Hugging Face's logo

mjm54
/
doom_health_gathering_supreme

Reinforcement Learning
sample-factory
TensorBoard
deep-reinforcement-learning
Eval Results
Model card Files Metrics Community
mjm54 commited on
Commit
db30fc7
·
verified ·
1 Parent(s): 020679b

Upload folder using huggingface_hub

Browse files
Files changed (9) hide show
  1. .gitattributes +1 -0
  2. .summary/0/events.out.tfevents.1739293094.ffa6c6e41717 +3 -0
  3. README.md +56 -3
  4. checkpoint_p0/best_000000827_3387392_reward_27.708.pth +3 -0
  5. checkpoint_p0/checkpoint_000000505_2068480.pth +3 -0
  6. checkpoint_p0/checkpoint_000000978_4005888.pth +3 -0
  7. config.json +142 -0
  8. replay.mp4 +3 -0
  9. sf_log.txt +782 -0
.gitattributes CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ replay.mp4 filter=lfs diff=lfs merge=lfs -text
.summary/0/events.out.tfevents.1739293094.ffa6c6e41717 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:897194d33f3bad38420a9952f23bb6422e6acdad4fd792f365712079dc6dfa49
3
+ size 198253
README.md CHANGED
@@ -1,3 +1,56 @@
1
- ---
2
- license: mit
3
- ---
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: sample-factory
3
+ tags:
4
+ - deep-reinforcement-learning
5
+ - reinforcement-learning
6
+ - sample-factory
7
+ model-index:
8
+ - name: APPO
9
+ results:
10
+ - task:
11
+ type: reinforcement-learning
12
+ name: reinforcement-learning
13
+ dataset:
14
+ name: doom_health_gathering_supreme
15
+ type: doom_health_gathering_supreme
16
+ metrics:
17
+ - type: mean_reward
18
+ value: 13.89 +/- 4.35
19
+ name: mean_reward
20
+ verified: false
21
+ ---
22
+
23
+ A(n) **APPO** model trained on the **doom_health_gathering_supreme** environment.
24
+
25
+ This model was trained using Sample-Factory 2.0: https://github.com/alex-petrenko/sample-factory.
26
+ Documentation for how to use Sample-Factory can be found at https://www.samplefactory.dev/
27
+
28
+
29
+ ## Downloading the model
30
+
31
+ After installing Sample-Factory, download the model with:
32
+ ```
33
+ python -m sample_factory.huggingface.load_from_hub -r mjm54/doom_health_gathering_supreme
34
+ ```
35
+
36
+
37
+ ## Using the model
38
+
39
+ To run the model after download, use the `enjoy` script corresponding to this environment:
40
+ ```
41
+ python -m <path.to.enjoy.module> --algo=APPO --env=doom_health_gathering_supreme --train_dir=./train_dir --experiment=doom_health_gathering_supreme
42
+ ```
43
+
44
+
45
+ You can also upload models to the Hugging Face Hub using the same script with the `--push_to_hub` flag.
46
+ See https://www.samplefactory.dev/10-huggingface/huggingface/ for more details
47
+
48
+ ## Training with this model
49
+
50
+ To continue training with this model, use the `train` script corresponding to this environment:
51
+ ```
52
+ python -m <path.to.train.module> --algo=APPO --env=doom_health_gathering_supreme --train_dir=./train_dir --experiment=doom_health_gathering_supreme --restart_behavior=resume --train_for_env_steps=10000000000
53
+ ```
54
+
55
+ Note, you may have to adjust `--train_for_env_steps` to a suitably high number as the experiment will resume at the number of steps it concluded at.
56
+
checkpoint_p0/best_000000827_3387392_reward_27.708.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:afed8cdd503fd7059f94471d3621d07e613df6976731b701db832384cd065e4b
3
+ size 34929051
checkpoint_p0/checkpoint_000000505_2068480.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:428047e09195c5740626f4d4d15de184d42003aea50fc2f3f9e755cc1dcd431e
3
+ size 34929541
checkpoint_p0/checkpoint_000000978_4005888.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d7827e5bb1c1e6f89e3cb9d64613ee737d4b6c834e99e2192abce710250ce279
3
+ size 34929477
config.json ADDED
@@ -0,0 +1,142 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "help": false,
3
+ "algo": "APPO",
4
+ "env": "doom_health_gathering_supreme",
5
+ "experiment": "default_experiment",
6
+ "train_dir": "/content/train_dir",
7
+ "restart_behavior": "resume",
8
+ "device": "gpu",
9
+ "seed": null,
10
+ "num_policies": 1,
11
+ "async_rl": true,
12
+ "serial_mode": false,
13
+ "batched_sampling": false,
14
+ "num_batches_to_accumulate": 2,
15
+ "worker_num_splits": 2,
16
+ "policy_workers_per_policy": 1,
17
+ "max_policy_lag": 1000,
18
+ "num_workers": 8,
19
+ "num_envs_per_worker": 4,
20
+ "batch_size": 1024,
21
+ "num_batches_per_epoch": 1,
22
+ "num_epochs": 1,
23
+ "rollout": 32,
24
+ "recurrence": 32,
25
+ "shuffle_minibatches": false,
26
+ "gamma": 0.99,
27
+ "reward_scale": 1.0,
28
+ "reward_clip": 1000.0,
29
+ "value_bootstrap": false,
30
+ "normalize_returns": true,
31
+ "exploration_loss_coeff": 0.001,
32
+ "value_loss_coeff": 0.5,
33
+ "kl_loss_coeff": 0.0,
34
+ "exploration_loss": "symmetric_kl",
35
+ "gae_lambda": 0.95,
36
+ "ppo_clip_ratio": 0.1,
37
+ "ppo_clip_value": 0.2,
38
+ "with_vtrace": false,
39
+ "vtrace_rho": 1.0,
40
+ "vtrace_c": 1.0,
41
+ "optimizer": "adam",
42
+ "adam_eps": 1e-06,
43
+ "adam_beta1": 0.9,
44
+ "adam_beta2": 0.999,
45
+ "max_grad_norm": 4.0,
46
+ "learning_rate": 0.0001,
47
+ "lr_schedule": "constant",
48
+ "lr_schedule_kl_threshold": 0.008,
49
+ "lr_adaptive_min": 1e-06,
50
+ "lr_adaptive_max": 0.01,
51
+ "obs_subtract_mean": 0.0,
52
+ "obs_scale": 255.0,
53
+ "normalize_input": true,
54
+ "normalize_input_keys": null,
55
+ "decorrelate_experience_max_seconds": 0,
56
+ "decorrelate_envs_on_one_worker": true,
57
+ "actor_worker_gpus": [],
58
+ "set_workers_cpu_affinity": true,
59
+ "force_envs_single_thread": false,
60
+ "default_niceness": 0,
61
+ "log_to_file": true,
62
+ "experiment_summaries_interval": 10,
63
+ "flush_summaries_interval": 30,
64
+ "stats_avg": 100,
65
+ "summaries_use_frameskip": true,
66
+ "heartbeat_interval": 20,
67
+ "heartbeat_reporting_interval": 600,
68
+ "train_for_env_steps": 4000000,
69
+ "train_for_seconds": 10000000000,
70
+ "save_every_sec": 120,
71
+ "keep_checkpoints": 2,
72
+ "load_checkpoint_kind": "latest",
73
+ "save_milestones_sec": -1,
74
+ "save_best_every_sec": 5,
75
+ "save_best_metric": "reward",
76
+ "save_best_after": 100000,
77
+ "benchmark": false,
78
+ "encoder_mlp_layers": [
79
+ 512,
80
+ 512
81
+ ],
82
+ "encoder_conv_architecture": "convnet_simple",
83
+ "encoder_conv_mlp_layers": [
84
+ 512
85
+ ],
86
+ "use_rnn": true,
87
+ "rnn_size": 512,
88
+ "rnn_type": "gru",
89
+ "rnn_num_layers": 1,
90
+ "decoder_mlp_layers": [],
91
+ "nonlinearity": "elu",
92
+ "policy_initialization": "orthogonal",
93
+ "policy_init_gain": 1.0,
94
+ "actor_critic_share_weights": true,
95
+ "adaptive_stddev": true,
96
+ "continuous_tanh_scale": 0.0,
97
+ "initial_stddev": 1.0,
98
+ "use_env_info_cache": false,
99
+ "env_gpu_actions": false,
100
+ "env_gpu_observations": true,
101
+ "env_frameskip": 4,
102
+ "env_framestack": 1,
103
+ "pixel_format": "CHW",
104
+ "use_record_episode_statistics": false,
105
+ "with_wandb": false,
106
+ "wandb_user": null,
107
+ "wandb_project": "sample_factory",
108
+ "wandb_group": null,
109
+ "wandb_job_type": "SF",
110
+ "wandb_tags": [],
111
+ "with_pbt": false,
112
+ "pbt_mix_policies_in_one_env": true,
113
+ "pbt_period_env_steps": 5000000,
114
+ "pbt_start_mutation": 20000000,
115
+ "pbt_replace_fraction": 0.3,
116
+ "pbt_mutation_rate": 0.15,
117
+ "pbt_replace_reward_gap": 0.1,
118
+ "pbt_replace_reward_gap_absolute": 1e-06,
119
+ "pbt_optimize_gamma": false,
120
+ "pbt_target_objective": "true_objective",
121
+ "pbt_perturb_min": 1.1,
122
+ "pbt_perturb_max": 1.5,
123
+ "num_agents": -1,
124
+ "num_humans": 0,
125
+ "num_bots": -1,
126
+ "start_bot_difficulty": null,
127
+ "timelimit": null,
128
+ "res_w": 128,
129
+ "res_h": 72,
130
+ "wide_aspect_ratio": false,
131
+ "eval_env_frameskip": 1,
132
+ "fps": 35,
133
+ "command_line": "--env=doom_health_gathering_supreme --num_workers=8 --num_envs_per_worker=4 --train_for_env_steps=4000000",
134
+ "cli_args": {
135
+ "env": "doom_health_gathering_supreme",
136
+ "num_workers": 8,
137
+ "num_envs_per_worker": 4,
138
+ "train_for_env_steps": 4000000
139
+ },
140
+ "git_hash": "unknown",
141
+ "git_repo_name": "not a git repository"
142
+ }
replay.mp4 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:55ddd575d0becac4187539ff60d80ffdd87c2bfcc4448bb138279dff0a413054
3
+ size 27331329
sf_log.txt ADDED
@@ -0,0 +1,782 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ [2025-02-11 16:58:19,123][02117] Saving configuration to /content/train_dir/default_experiment/config.json...
2
+ [2025-02-11 16:58:19,125][02117] Rollout worker 0 uses device cpu
3
+ [2025-02-11 16:58:19,126][02117] Rollout worker 1 uses device cpu
4
+ [2025-02-11 16:58:19,128][02117] Rollout worker 2 uses device cpu
5
+ [2025-02-11 16:58:19,129][02117] Rollout worker 3 uses device cpu
6
+ [2025-02-11 16:58:19,130][02117] Rollout worker 4 uses device cpu
7
+ [2025-02-11 16:58:19,131][02117] Rollout worker 5 uses device cpu
8
+ [2025-02-11 16:58:19,133][02117] Rollout worker 6 uses device cpu
9
+ [2025-02-11 16:58:19,135][02117] Rollout worker 7 uses device cpu
10
+ [2025-02-11 16:58:19,247][02117] Using GPUs [0] for process 0 (actually maps to GPUs [0])
11
+ [2025-02-11 16:58:19,248][02117] InferenceWorker_p0-w0: min num requests: 2
12
+ [2025-02-11 16:58:19,281][02117] Starting all processes...
13
+ [2025-02-11 16:58:19,282][02117] Starting process learner_proc0
14
+ [2025-02-11 16:58:19,341][02117] Starting all processes...
15
+ [2025-02-11 16:58:19,346][02117] Starting process inference_proc0-0
16
+ [2025-02-11 16:58:19,347][02117] Starting process rollout_proc0
17
+ [2025-02-11 16:58:19,348][02117] Starting process rollout_proc1
18
+ [2025-02-11 16:58:19,349][02117] Starting process rollout_proc2
19
+ [2025-02-11 16:58:19,349][02117] Starting process rollout_proc3
20
+ [2025-02-11 16:58:19,349][02117] Starting process rollout_proc4
21
+ [2025-02-11 16:58:19,351][02117] Starting process rollout_proc5
22
+ [2025-02-11 16:58:19,352][02117] Starting process rollout_proc6
23
+ [2025-02-11 16:58:19,356][02117] Starting process rollout_proc7
24
+ [2025-02-11 16:58:22,077][04730] Using GPUs [0] for process 0 (actually maps to GPUs [0])
25
+ [2025-02-11 16:58:22,077][04730] Set environment var CUDA_VISIBLE_DEVICES to '0' (GPU indices [0]) for inference process 0
26
+ [2025-02-11 16:58:22,099][04730] Num visible devices: 1
27
+ [2025-02-11 16:58:22,187][04733] Worker 2 uses CPU cores [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11]
28
+ [2025-02-11 16:58:22,239][04734] Worker 3 uses CPU cores [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11]
29
+ [2025-02-11 16:58:22,253][04731] Worker 1 uses CPU cores [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11]
30
+ [2025-02-11 16:58:22,418][04717] Using GPUs [0] for process 0 (actually maps to GPUs [0])
31
+ [2025-02-11 16:58:22,418][04717] Set environment var CUDA_VISIBLE_DEVICES to '0' (GPU indices [0]) for learning process 0
32
+ [2025-02-11 16:58:22,438][04717] Num visible devices: 1
33
+ [2025-02-11 16:58:22,439][04737] Worker 6 uses CPU cores [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11]
34
+ [2025-02-11 16:58:22,450][04732] Worker 0 uses CPU cores [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11]
35
+ [2025-02-11 16:58:22,473][04717] Starting seed is not provided
36
+ [2025-02-11 16:58:22,474][04717] Using GPUs [0] for process 0 (actually maps to GPUs [0])
37
+ [2025-02-11 16:58:22,474][04717] Initializing actor-critic model on device cuda:0
38
+ [2025-02-11 16:58:22,474][04717] RunningMeanStd input shape: (3, 72, 128)
39
+ [2025-02-11 16:58:22,478][04717] RunningMeanStd input shape: (1,)
40
+ [2025-02-11 16:58:22,488][04736] Worker 5 uses CPU cores [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11]
41
+ [2025-02-11 16:58:22,492][04717] ConvEncoder: input_channels=3
42
+ [2025-02-11 16:58:22,532][04735] Worker 4 uses CPU cores [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11]
43
+ [2025-02-11 16:58:22,538][04738] Worker 7 uses CPU cores [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11]
44
+ [2025-02-11 16:58:22,783][04717] Conv encoder output size: 512
45
+ [2025-02-11 16:58:22,783][04717] Policy head output size: 512
46
+ [2025-02-11 16:58:22,843][04717] Created Actor Critic model with architecture:
47
+ [2025-02-11 16:58:22,843][04717] ActorCriticSharedWeights(
48
+ (obs_normalizer): ObservationNormalizer(
49
+ (running_mean_std): RunningMeanStdDictInPlace(
50
+ (running_mean_std): ModuleDict(
51
+ (obs): RunningMeanStdInPlace()
52
+ )
53
+ )
54
+ )
55
+ (returns_normalizer): RecursiveScriptModule(original_name=RunningMeanStdInPlace)
56
+ (encoder): VizdoomEncoder(
57
+ (basic_encoder): ConvEncoder(
58
+ (enc): RecursiveScriptModule(
59
+ original_name=ConvEncoderImpl
60
+ (conv_head): RecursiveScriptModule(
61
+ original_name=Sequential
62
+ (0): RecursiveScriptModule(original_name=Conv2d)
63
+ (1): RecursiveScriptModule(original_name=ELU)
64
+ (2): RecursiveScriptModule(original_name=Conv2d)
65
+ (3): RecursiveScriptModule(original_name=ELU)
66
+ (4): RecursiveScriptModule(original_name=Conv2d)
67
+ (5): RecursiveScriptModule(original_name=ELU)
68
+ )
69
+ (mlp_layers): RecursiveScriptModule(
70
+ original_name=Sequential
71
+ (0): RecursiveScriptModule(original_name=Linear)
72
+ (1): RecursiveScriptModule(original_name=ELU)
73
+ )
74
+ )
75
+ )
76
+ )
77
+ (core): ModelCoreRNN(
78
+ (core): GRU(512, 512)
79
+ )
80
+ (decoder): MlpDecoder(
81
+ (mlp): Identity()
82
+ )
83
+ (critic_linear): Linear(in_features=512, out_features=1, bias=True)
84
+ (action_parameterization): ActionParameterizationDefault(
85
+ (distribution_linear): Linear(in_features=512, out_features=5, bias=True)
86
+ )
87
+ )
88
+ [2025-02-11 16:58:23,065][04717] Using optimizer <class 'torch.optim.adam.Adam'>
89
+ [2025-02-11 16:58:27,331][04717] No checkpoints found
90
+ [2025-02-11 16:58:27,331][04717] Did not load from checkpoint, starting from scratch!
91
+ [2025-02-11 16:58:27,331][04717] Initialized policy 0 weights for model version 0
92
+ [2025-02-11 16:58:27,333][04717] LearnerWorker_p0 finished initialization!
93
+ [2025-02-11 16:58:27,333][04717] Using GPUs [0] for process 0 (actually maps to GPUs [0])
94
+ [2025-02-11 16:58:27,415][04730] RunningMeanStd input shape: (3, 72, 128)
95
+ [2025-02-11 16:58:27,416][04730] RunningMeanStd input shape: (1,)
96
+ [2025-02-11 16:58:27,427][04730] ConvEncoder: input_channels=3
97
+ [2025-02-11 16:58:27,530][04730] Conv encoder output size: 512
98
+ [2025-02-11 16:58:27,531][04730] Policy head output size: 512
99
+ [2025-02-11 16:58:27,566][02117] Inference worker 0-0 is ready!
100
+ [2025-02-11 16:58:27,567][02117] All inference workers are ready! Signal rollout workers to start!
101
+ [2025-02-11 16:58:27,609][04734] Doom resolution: 160x120, resize resolution: (128, 72)
102
+ [2025-02-11 16:58:27,610][04733] Doom resolution: 160x120, resize resolution: (128, 72)
103
+ [2025-02-11 16:58:27,620][04736] Doom resolution: 160x120, resize resolution: (128, 72)
104
+ [2025-02-11 16:58:27,620][04737] Doom resolution: 160x120, resize resolution: (128, 72)
105
+ [2025-02-11 16:58:27,620][04731] Doom resolution: 160x120, resize resolution: (128, 72)
106
+ [2025-02-11 16:58:27,621][04735] Doom resolution: 160x120, resize resolution: (128, 72)
107
+ [2025-02-11 16:58:27,622][04738] Doom resolution: 160x120, resize resolution: (128, 72)
108
+ [2025-02-11 16:58:27,622][04732] Doom resolution: 160x120, resize resolution: (128, 72)
109
+ [2025-02-11 16:58:27,943][04733] Decorrelating experience for 0 frames...
110
+ [2025-02-11 16:58:27,943][04731] Decorrelating experience for 0 frames...
111
+ [2025-02-11 16:58:27,943][04736] Decorrelating experience for 0 frames...
112
+ [2025-02-11 16:58:27,943][04737] Decorrelating experience for 0 frames...
113
+ [2025-02-11 16:58:27,943][04735] Decorrelating experience for 0 frames...
114
+ [2025-02-11 16:58:27,943][04734] Decorrelating experience for 0 frames...
115
+ [2025-02-11 16:58:28,176][04732] Decorrelating experience for 0 frames...
116
+ [2025-02-11 16:58:28,204][04735] Decorrelating experience for 32 frames...
117
+ [2025-02-11 16:58:28,211][04736] Decorrelating experience for 32 frames...
118
+ [2025-02-11 16:58:28,211][04733] Decorrelating experience for 32 frames...
119
+ [2025-02-11 16:58:28,218][04737] Decorrelating experience for 32 frames...
120
+ [2025-02-11 16:58:28,219][04734] Decorrelating experience for 32 frames...
121
+ [2025-02-11 16:58:28,440][04732] Decorrelating experience for 32 frames...
122
+ [2025-02-11 16:58:28,506][04738] Decorrelating experience for 0 frames...
123
+ [2025-02-11 16:58:28,560][04733] Decorrelating experience for 64 frames...
124
+ [2025-02-11 16:58:28,561][04734] Decorrelating experience for 64 frames...
125
+ [2025-02-11 16:58:28,685][04737] Decorrelating experience for 64 frames...
126
+ [2025-02-11 16:58:28,756][04738] Decorrelating experience for 32 frames...
127
+ [2025-02-11 16:58:28,766][04732] Decorrelating experience for 64 frames...
128
+ [2025-02-11 16:58:28,772][04736] Decorrelating experience for 64 frames...
129
+ [2025-02-11 16:58:28,889][04733] Decorrelating experience for 96 frames...
130
+ [2025-02-11 16:58:28,999][04737] Decorrelating experience for 96 frames...
131
+ [2025-02-11 16:58:29,008][04734] Decorrelating experience for 96 frames...
132
+ [2025-02-11 16:58:29,047][04735] Decorrelating experience for 64 frames...
133
+ [2025-02-11 16:58:29,165][04738] Decorrelating experience for 64 frames...
134
+ [2025-02-11 16:58:29,281][04732] Decorrelating experience for 96 frames...
135
+ [2025-02-11 16:58:29,294][04731] Decorrelating experience for 32 frames...
136
+ [2025-02-11 16:58:29,329][04735] Decorrelating experience for 96 frames...
137
+ [2025-02-11 16:58:29,477][04738] Decorrelating experience for 96 frames...
138
+ [2025-02-11 16:58:29,570][04736] Decorrelating experience for 96 frames...
139
+ [2025-02-11 16:58:29,591][02117] Fps is (10 sec: nan, 60 sec: nan, 300 sec: nan). Total num frames: 0. Throughput: 0: nan. Samples: 0. Policy #0 lag: (min: -1.0, avg: -1.0, max: -1.0)
140
+ [2025-02-11 16:58:29,637][04731] Decorrelating experience for 64 frames...
141
+ [2025-02-11 16:58:29,914][04731] Decorrelating experience for 96 frames...
142
+ [2025-02-11 16:58:30,515][04717] Signal inference workers to stop experience collection...
143
+ [2025-02-11 16:58:30,521][04730] InferenceWorker_p0-w0: stopping experience collection
144
+ [2025-02-11 16:58:31,874][04717] Signal inference workers to resume experience collection...
145
+ [2025-02-11 16:58:31,874][04730] InferenceWorker_p0-w0: resuming experience collection
146
+ [2025-02-11 16:58:33,649][04730] Updated weights for policy 0, policy_version 10 (0.0091)
147
+ [2025-02-11 16:58:34,591][02117] Fps is (10 sec: 11468.5, 60 sec: 11468.5, 300 sec: 11468.5). Total num frames: 57344. Throughput: 0: 2059.2. Samples: 10296. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0)
148
+ [2025-02-11 16:58:34,594][02117] Avg episode reward: [(0, '4.406')]
149
+ [2025-02-11 16:58:35,801][04730] Updated weights for policy 0, policy_version 20 (0.0011)
150
+ [2025-02-11 16:58:37,831][04730] Updated weights for policy 0, policy_version 30 (0.0012)
151
+ [2025-02-11 16:58:39,239][02117] Heartbeat connected on Batcher_0
152
+ [2025-02-11 16:58:39,253][02117] Heartbeat connected on InferenceWorker_p0-w0
153
+ [2025-02-11 16:58:39,255][02117] Heartbeat connected on RolloutWorker_w0
154
+ [2025-02-11 16:58:39,258][02117] Heartbeat connected on RolloutWorker_w1
155
+ [2025-02-11 16:58:39,265][02117] Heartbeat connected on RolloutWorker_w3
156
+ [2025-02-11 16:58:39,267][02117] Heartbeat connected on RolloutWorker_w2
157
+ [2025-02-11 16:58:39,270][02117] Heartbeat connected on LearnerWorker_p0
158
+ [2025-02-11 16:58:39,272][02117] Heartbeat connected on RolloutWorker_w4
159
+ [2025-02-11 16:58:39,274][02117] Heartbeat connected on RolloutWorker_w5
160
+ [2025-02-11 16:58:39,277][02117] Heartbeat connected on RolloutWorker_w6
161
+ [2025-02-11 16:58:39,281][02117] Heartbeat connected on RolloutWorker_w7
162
+ [2025-02-11 16:58:39,591][02117] Fps is (10 sec: 15564.6, 60 sec: 15564.6, 300 sec: 15564.6). Total num frames: 155648. Throughput: 0: 3989.2. Samples: 39892. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0)
163
+ [2025-02-11 16:58:39,593][02117] Avg episode reward: [(0, '4.354')]
164
+ [2025-02-11 16:58:39,595][04717] Saving new best policy, reward=4.354!
165
+ [2025-02-11 16:58:39,882][04730] Updated weights for policy 0, policy_version 40 (0.0011)
166
+ [2025-02-11 16:58:41,914][04730] Updated weights for policy 0, policy_version 50 (0.0012)
167
+ [2025-02-11 16:58:44,017][04730] Updated weights for policy 0, policy_version 60 (0.0012)
168
+ [2025-02-11 16:58:44,591][02117] Fps is (10 sec: 19660.8, 60 sec: 16930.0, 300 sec: 16930.0). Total num frames: 253952. Throughput: 0: 3656.8. Samples: 54852. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0)
169
+ [2025-02-11 16:58:44,594][02117] Avg episode reward: [(0, '4.916')]
170
+ [2025-02-11 16:58:44,632][04717] Saving new best policy, reward=4.916!
171
+ [2025-02-11 16:58:46,073][04730] Updated weights for policy 0, policy_version 70 (0.0012)
172
+ [2025-02-11 16:58:48,187][04730] Updated weights for policy 0, policy_version 80 (0.0012)
173
+ [2025-02-11 16:58:49,591][02117] Fps is (10 sec: 19661.0, 60 sec: 17612.8, 300 sec: 17612.8). Total num frames: 352256. Throughput: 0: 4224.2. Samples: 84484. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
174
+ [2025-02-11 16:58:49,593][02117] Avg episode reward: [(0, '4.411')]
175
+ [2025-02-11 16:58:50,261][04730] Updated weights for policy 0, policy_version 90 (0.0011)
176
+ [2025-02-11 16:58:52,302][04730] Updated weights for policy 0, policy_version 100 (0.0012)
177
+ [2025-02-11 16:58:54,339][04730] Updated weights for policy 0, policy_version 110 (0.0012)
178
+ [2025-02-11 16:58:54,591][02117] Fps is (10 sec: 20070.4, 60 sec: 18186.2, 300 sec: 18186.2). Total num frames: 454656. Throughput: 0: 4584.7. Samples: 114618. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0)
179
+ [2025-02-11 16:58:54,593][02117] Avg episode reward: [(0, '5.041')]
180
+ [2025-02-11 16:58:54,600][04717] Saving new best policy, reward=5.041!
181
+ [2025-02-11 16:58:56,397][04730] Updated weights for policy 0, policy_version 120 (0.0012)
182
+ [2025-02-11 16:58:58,458][04730] Updated weights for policy 0, policy_version 130 (0.0012)
183
+ [2025-02-11 16:58:59,591][02117] Fps is (10 sec: 20070.4, 60 sec: 18432.0, 300 sec: 18432.0). Total num frames: 552960. Throughput: 0: 4319.6. Samples: 129588. Policy #0 lag: (min: 0.0, avg: 0.9, max: 2.0)
184
+ [2025-02-11 16:58:59,592][02117] Avg episode reward: [(0, '5.187')]
185
+ [2025-02-11 16:58:59,596][04717] Saving new best policy, reward=5.187!
186
+ [2025-02-11 16:59:00,573][04730] Updated weights for policy 0, policy_version 140 (0.0012)
187
+ [2025-02-11 16:59:02,651][04730] Updated weights for policy 0, policy_version 150 (0.0011)
188
+ [2025-02-11 16:59:04,591][02117] Fps is (10 sec: 19660.8, 60 sec: 18607.5, 300 sec: 18607.5). Total num frames: 651264. Throughput: 0: 4546.2. Samples: 159118. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0)
189
+ [2025-02-11 16:59:04,593][02117] Avg episode reward: [(0, '5.322')]
190
+ [2025-02-11 16:59:04,599][04717] Saving new best policy, reward=5.322!
191
+ [2025-02-11 16:59:04,725][04730] Updated weights for policy 0, policy_version 160 (0.0012)
192
+ [2025-02-11 16:59:06,685][04730] Updated weights for policy 0, policy_version 170 (0.0011)
193
+ [2025-02-11 16:59:08,703][04730] Updated weights for policy 0, policy_version 180 (0.0012)
194
+ [2025-02-11 16:59:09,591][02117] Fps is (10 sec: 20070.4, 60 sec: 18841.6, 300 sec: 18841.6). Total num frames: 753664. Throughput: 0: 4740.0. Samples: 189600. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0)
195
+ [2025-02-11 16:59:09,594][02117] Avg episode reward: [(0, '5.649')]
196
+ [2025-02-11 16:59:09,596][04717] Saving new best policy, reward=5.649!
197
+ [2025-02-11 16:59:10,701][04730] Updated weights for policy 0, policy_version 190 (0.0011)
198
+ [2025-02-11 16:59:12,765][04730] Updated weights for policy 0, policy_version 200 (0.0012)
199
+ [2025-02-11 16:59:14,591][02117] Fps is (10 sec: 20070.3, 60 sec: 18932.6, 300 sec: 18932.6). Total num frames: 851968. Throughput: 0: 4547.4. Samples: 204632. Policy #0 lag: (min: 0.0, avg: 0.7, max: 1.0)
200
+ [2025-02-11 16:59:14,594][02117] Avg episode reward: [(0, '7.183')]
201
+ [2025-02-11 16:59:14,601][04717] Saving new best policy, reward=7.183!
202
+ [2025-02-11 16:59:14,895][04730] Updated weights for policy 0, policy_version 210 (0.0011)
203
+ [2025-02-11 16:59:16,906][04730] Updated weights for policy 0, policy_version 220 (0.0011)
204
+ [2025-02-11 16:59:18,910][04730] Updated weights for policy 0, policy_version 230 (0.0011)
205
+ [2025-02-11 16:59:19,591][02117] Fps is (10 sec: 20070.4, 60 sec: 19087.3, 300 sec: 19087.3). Total num frames: 954368. Throughput: 0: 4981.7. Samples: 234470. Policy #0 lag: (min: 0.0, avg: 0.7, max: 1.0)
206
+ [2025-02-11 16:59:19,593][02117] Avg episode reward: [(0, '7.850')]
207
+ [2025-02-11 16:59:19,595][04717] Saving new best policy, reward=7.850!
208
+ [2025-02-11 16:59:20,937][04730] Updated weights for policy 0, policy_version 240 (0.0012)
209
+ [2025-02-11 16:59:22,946][04730] Updated weights for policy 0, policy_version 250 (0.0012)
210
+ [2025-02-11 16:59:24,591][02117] Fps is (10 sec: 20480.1, 60 sec: 19213.9, 300 sec: 19213.9). Total num frames: 1056768. Throughput: 0: 4998.8. Samples: 264838. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0)
211
+ [2025-02-11 16:59:24,593][02117] Avg episode reward: [(0, '8.006')]
212
+ [2025-02-11 16:59:24,600][04717] Saving new best policy, reward=8.006!
213
+ [2025-02-11 16:59:25,009][04730] Updated weights for policy 0, policy_version 260 (0.0012)
214
+ [2025-02-11 16:59:27,111][04730] Updated weights for policy 0, policy_version 270 (0.0012)
215
+ [2025-02-11 16:59:29,119][04730] Updated weights for policy 0, policy_version 280 (0.0011)
216
+ [2025-02-11 16:59:29,591][02117] Fps is (10 sec: 20070.4, 60 sec: 19251.2, 300 sec: 19251.2). Total num frames: 1155072. Throughput: 0: 4994.5. Samples: 279602. Policy #0 lag: (min: 0.0, avg: 0.8, max: 1.0)
217
+ [2025-02-11 16:59:29,593][02117] Avg episode reward: [(0, '9.474')]
218
+ [2025-02-11 16:59:29,596][04717] Saving new best policy, reward=9.474!
219
+ [2025-02-11 16:59:31,146][04730] Updated weights for policy 0, policy_version 290 (0.0012)
220
+ [2025-02-11 16:59:33,153][04730] Updated weights for policy 0, policy_version 300 (0.0011)
221
+ [2025-02-11 16:59:34,591][02117] Fps is (10 sec: 20070.3, 60 sec: 20002.1, 300 sec: 19345.7). Total num frames: 1257472. Throughput: 0: 5012.0. Samples: 310026. Policy #0 lag: (min: 0.0, avg: 0.7, max: 1.0)
222
+ [2025-02-11 16:59:34,593][02117] Avg episode reward: [(0, '10.984')]
223
+ [2025-02-11 16:59:34,601][04717] Saving new best policy, reward=10.984!
224
+ [2025-02-11 16:59:35,151][04730] Updated weights for policy 0, policy_version 310 (0.0012)
225
+ [2025-02-11 16:59:37,170][04730] Updated weights for policy 0, policy_version 320 (0.0012)
226
+ [2025-02-11 16:59:39,312][04730] Updated weights for policy 0, policy_version 330 (0.0011)
227
+ [2025-02-11 16:59:39,591][02117] Fps is (10 sec: 20070.2, 60 sec: 20002.1, 300 sec: 19368.2). Total num frames: 1355776. Throughput: 0: 5008.7. Samples: 340008. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
228
+ [2025-02-11 16:59:39,593][02117] Avg episode reward: [(0, '12.348')]
229
+ [2025-02-11 16:59:39,595][04717] Saving new best policy, reward=12.348!
230
+ [2025-02-11 16:59:41,328][04730] Updated weights for policy 0, policy_version 340 (0.0011)
231
+ [2025-02-11 16:59:43,318][04730] Updated weights for policy 0, policy_version 350 (0.0012)
232
+ [2025-02-11 16:59:44,591][02117] Fps is (10 sec: 20070.4, 60 sec: 20070.4, 300 sec: 19442.3). Total num frames: 1458176. Throughput: 0: 5017.1. Samples: 355360. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0)
233
+ [2025-02-11 16:59:44,593][02117] Avg episode reward: [(0, '16.962')]
234
+ [2025-02-11 16:59:44,599][04717] Saving new best policy, reward=16.962!
235
+ [2025-02-11 16:59:45,359][04730] Updated weights for policy 0, policy_version 360 (0.0011)
236
+ [2025-02-11 16:59:47,346][04730] Updated weights for policy 0, policy_version 370 (0.0011)
237
+ [2025-02-11 16:59:49,324][04730] Updated weights for policy 0, policy_version 380 (0.0011)
238
+ [2025-02-11 16:59:49,591][02117] Fps is (10 sec: 20479.9, 60 sec: 20138.6, 300 sec: 19507.2). Total num frames: 1560576. Throughput: 0: 5041.5. Samples: 385986. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
239
+ [2025-02-11 16:59:49,593][02117] Avg episode reward: [(0, '17.832')]
240
+ [2025-02-11 16:59:49,596][04717] Saving new best policy, reward=17.832!
241
+ [2025-02-11 16:59:51,439][04730] Updated weights for policy 0, policy_version 390 (0.0012)
242
+ [2025-02-11 16:59:53,484][04730] Updated weights for policy 0, policy_version 400 (0.0012)
243
+ [2025-02-11 16:59:54,591][02117] Fps is (10 sec: 20070.4, 60 sec: 20070.4, 300 sec: 19516.2). Total num frames: 1658880. Throughput: 0: 5029.1. Samples: 415908. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
244
+ [2025-02-11 16:59:54,593][02117] Avg episode reward: [(0, '16.814')]
245
+ [2025-02-11 16:59:55,508][04730] Updated weights for policy 0, policy_version 410 (0.0012)
246
+ [2025-02-11 16:59:57,516][04730] Updated weights for policy 0, policy_version 420 (0.0012)
247
+ [2025-02-11 16:59:59,493][04730] Updated weights for policy 0, policy_version 430 (0.0011)
248
+ [2025-02-11 16:59:59,591][02117] Fps is (10 sec: 20070.5, 60 sec: 20138.6, 300 sec: 19569.8). Total num frames: 1761280. Throughput: 0: 5034.8. Samples: 431198. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0)
249
+ [2025-02-11 16:59:59,592][02117] Avg episode reward: [(0, '20.721')]
250
+ [2025-02-11 16:59:59,596][04717] Saving new best policy, reward=20.721!
251
+ [2025-02-11 17:00:01,494][04730] Updated weights for policy 0, policy_version 440 (0.0011)
252
+ [2025-02-11 17:00:03,555][04730] Updated weights for policy 0, policy_version 450 (0.0012)
253
+ [2025-02-11 17:00:04,591][02117] Fps is (10 sec: 20070.3, 60 sec: 20138.7, 300 sec: 19574.5). Total num frames: 1859584. Throughput: 0: 5051.1. Samples: 461768. Policy #0 lag: (min: 0.0, avg: 0.9, max: 2.0)
254
+ [2025-02-11 17:00:04,593][02117] Avg episode reward: [(0, '19.242')]
255
+ [2025-02-11 17:00:05,622][04730] Updated weights for policy 0, policy_version 460 (0.0011)
256
+ [2025-02-11 17:00:07,592][04730] Updated weights for policy 0, policy_version 470 (0.0012)
257
+ [2025-02-11 17:00:09,582][04730] Updated weights for policy 0, policy_version 480 (0.0012)
258
+ [2025-02-11 17:00:09,591][02117] Fps is (10 sec: 20480.2, 60 sec: 20206.9, 300 sec: 19660.8). Total num frames: 1966080. Throughput: 0: 5057.7. Samples: 492434. Policy #0 lag: (min: 0.0, avg: 0.9, max: 2.0)
259
+ [2025-02-11 17:00:09,592][02117] Avg episode reward: [(0, '19.533')]
260
+ [2025-02-11 17:00:11,583][04730] Updated weights for policy 0, policy_version 490 (0.0011)
261
+ [2025-02-11 17:00:13,593][04730] Updated weights for policy 0, policy_version 500 (0.0012)
262
+ [2025-02-11 17:00:14,591][02117] Fps is (10 sec: 20889.9, 60 sec: 20275.3, 300 sec: 19699.8). Total num frames: 2068480. Throughput: 0: 5071.8. Samples: 507832. Policy #0 lag: (min: 0.0, avg: 0.9, max: 2.0)
263
+ [2025-02-11 17:00:14,592][02117] Avg episode reward: [(0, '17.718')]
264
+ [2025-02-11 17:00:14,599][04717] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000505_2068480.pth...
265
+ [2025-02-11 17:00:15,631][04730] Updated weights for policy 0, policy_version 510 (0.0011)
266
+ [2025-02-11 17:00:17,716][04730] Updated weights for policy 0, policy_version 520 (0.0011)
267
+ [2025-02-11 17:00:19,591][02117] Fps is (10 sec: 20070.2, 60 sec: 20206.9, 300 sec: 19698.0). Total num frames: 2166784. Throughput: 0: 5063.2. Samples: 537868. Policy #0 lag: (min: 0.0, avg: 0.9, max: 2.0)
268
+ [2025-02-11 17:00:19,593][02117] Avg episode reward: [(0, '19.044')]
269
+ [2025-02-11 17:00:19,699][04730] Updated weights for policy 0, policy_version 530 (0.0011)
270
+ [2025-02-11 17:00:21,691][04730] Updated weights for policy 0, policy_version 540 (0.0012)
271
+ [2025-02-11 17:00:23,667][04730] Updated weights for policy 0, policy_version 550 (0.0012)
272
+ [2025-02-11 17:00:24,591][02117] Fps is (10 sec: 20070.1, 60 sec: 20206.9, 300 sec: 19732.0). Total num frames: 2269184. Throughput: 0: 5083.7. Samples: 568776. Policy #0 lag: (min: 0.0, avg: 0.9, max: 2.0)
273
+ [2025-02-11 17:00:24,593][02117] Avg episode reward: [(0, '22.192')]
274
+ [2025-02-11 17:00:24,600][04717] Saving new best policy, reward=22.192!
275
+ [2025-02-11 17:00:25,657][04730] Updated weights for policy 0, policy_version 560 (0.0012)
276
+ [2025-02-11 17:00:27,633][04730] Updated weights for policy 0, policy_version 570 (0.0011)
277
+ [2025-02-11 17:00:29,591][02117] Fps is (10 sec: 20480.2, 60 sec: 20275.2, 300 sec: 19763.2). Total num frames: 2371584. Throughput: 0: 5085.0. Samples: 584186. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0)
278
+ [2025-02-11 17:00:29,593][02117] Avg episode reward: [(0, '20.078')]
279
+ [2025-02-11 17:00:29,675][04730] Updated weights for policy 0, policy_version 580 (0.0011)
280
+ [2025-02-11 17:00:31,723][04730] Updated weights for policy 0, policy_version 590 (0.0011)
281
+ [2025-02-11 17:00:33,742][04730] Updated weights for policy 0, policy_version 600 (0.0011)
282
+ [2025-02-11 17:00:34,591][02117] Fps is (10 sec: 20480.3, 60 sec: 20275.2, 300 sec: 19791.9). Total num frames: 2473984. Throughput: 0: 5075.5. Samples: 614384. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0)
283
+ [2025-02-11 17:00:34,592][02117] Avg episode reward: [(0, '22.330')]
284
+ [2025-02-11 17:00:34,601][04717] Saving new best policy, reward=22.208!
285
+ [2025-02-11 17:00:35,756][04730] Updated weights for policy 0, policy_version 610 (0.0011)
286
+ [2025-02-11 17:00:37,760][04730] Updated weights for policy 0, policy_version 620 (0.0011)
287
+ [2025-02-11 17:00:39,591][02117] Fps is (10 sec: 20480.1, 60 sec: 20343.5, 300 sec: 19818.3). Total num frames: 2576384. Throughput: 0: 5092.9. Samples: 645086. Policy #0 lag: (min: 0.0, avg: 0.9, max: 2.0)
288
+ [2025-02-11 17:00:39,593][02117] Avg episode reward: [(0, '23.133')]
289
+ [2025-02-11 17:00:39,595][04717] Saving new best policy, reward=23.133!
290
+ [2025-02-11 17:00:39,740][04730] Updated weights for policy 0, policy_version 630 (0.0012)
291
+ [2025-02-11 17:00:41,780][04730] Updated weights for policy 0, policy_version 640 (0.0012)
292
+ [2025-02-11 17:00:43,832][04730] Updated weights for policy 0, policy_version 650 (0.0012)
293
+ [2025-02-11 17:00:44,591][02117] Fps is (10 sec: 20070.0, 60 sec: 20275.2, 300 sec: 19812.5). Total num frames: 2674688. Throughput: 0: 5084.3. Samples: 659990. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
294
+ [2025-02-11 17:00:44,594][02117] Avg episode reward: [(0, '24.806')]
295
+ [2025-02-11 17:00:44,600][04717] Saving new best policy, reward=24.806!
296
+ [2025-02-11 17:00:45,849][04730] Updated weights for policy 0, policy_version 660 (0.0012)
297
+ [2025-02-11 17:00:47,837][04730] Updated weights for policy 0, policy_version 670 (0.0012)
298
+ [2025-02-11 17:00:49,591][02117] Fps is (10 sec: 20070.3, 60 sec: 20275.2, 300 sec: 19836.3). Total num frames: 2777088. Throughput: 0: 5086.9. Samples: 690680. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
299
+ [2025-02-11 17:00:49,592][02117] Avg episode reward: [(0, '22.971')]
300
+ [2025-02-11 17:00:49,820][04730] Updated weights for policy 0, policy_version 680 (0.0011)
301
+ [2025-02-11 17:00:51,818][04730] Updated weights for policy 0, policy_version 690 (0.0011)
302
+ [2025-02-11 17:00:53,843][04730] Updated weights for policy 0, policy_version 700 (0.0011)
303
+ [2025-02-11 17:00:54,591][02117] Fps is (10 sec: 20480.2, 60 sec: 20343.5, 300 sec: 19858.5). Total num frames: 2879488. Throughput: 0: 5083.0. Samples: 721168. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
304
+ [2025-02-11 17:00:54,593][02117] Avg episode reward: [(0, '22.836')]
305
+ [2025-02-11 17:00:55,903][04730] Updated weights for policy 0, policy_version 710 (0.0011)
306
+ [2025-02-11 17:00:57,926][04730] Updated weights for policy 0, policy_version 720 (0.0011)
307
+ [2025-02-11 17:00:59,591][02117] Fps is (10 sec: 20479.8, 60 sec: 20343.5, 300 sec: 19879.2). Total num frames: 2981888. Throughput: 0: 5076.0. Samples: 736252. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0)
308
+ [2025-02-11 17:00:59,593][02117] Avg episode reward: [(0, '25.789')]
309
+ [2025-02-11 17:00:59,596][04717] Saving new best policy, reward=25.789!
310
+ [2025-02-11 17:00:59,915][04730] Updated weights for policy 0, policy_version 730 (0.0011)
311
+ [2025-02-11 17:01:01,897][04730] Updated weights for policy 0, policy_version 740 (0.0012)
312
+ [2025-02-11 17:01:03,868][04730] Updated weights for policy 0, policy_version 750 (0.0011)
313
+ [2025-02-11 17:01:04,591][02117] Fps is (10 sec: 20479.9, 60 sec: 20411.7, 300 sec: 19898.6). Total num frames: 3084288. Throughput: 0: 5095.6. Samples: 767168. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
314
+ [2025-02-11 17:01:04,593][02117] Avg episode reward: [(0, '24.300')]
315
+ [2025-02-11 17:01:05,874][04730] Updated weights for policy 0, policy_version 760 (0.0011)
316
+ [2025-02-11 17:01:08,006][04730] Updated weights for policy 0, policy_version 770 (0.0012)
317
+ [2025-02-11 17:01:09,591][02117] Fps is (10 sec: 20070.4, 60 sec: 20275.2, 300 sec: 19891.2). Total num frames: 3182592. Throughput: 0: 5073.1. Samples: 797064. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
318
+ [2025-02-11 17:01:09,594][02117] Avg episode reward: [(0, '26.269')]
319
+ [2025-02-11 17:01:09,596][04717] Saving new best policy, reward=26.269!
320
+ [2025-02-11 17:01:10,073][04730] Updated weights for policy 0, policy_version 780 (0.0012)
321
+ [2025-02-11 17:01:12,071][04730] Updated weights for policy 0, policy_version 790 (0.0012)
322
+ [2025-02-11 17:01:14,072][04730] Updated weights for policy 0, policy_version 800 (0.0011)
323
+ [2025-02-11 17:01:14,591][02117] Fps is (10 sec: 20070.5, 60 sec: 20275.2, 300 sec: 19909.0). Total num frames: 3284992. Throughput: 0: 5068.6. Samples: 812272. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
324
+ [2025-02-11 17:01:14,593][02117] Avg episode reward: [(0, '26.525')]
325
+ [2025-02-11 17:01:14,600][04717] Saving new best policy, reward=26.525!
326
+ [2025-02-11 17:01:16,076][04730] Updated weights for policy 0, policy_version 810 (0.0011)
327
+ [2025-02-11 17:01:18,085][04730] Updated weights for policy 0, policy_version 820 (0.0011)
328
+ [2025-02-11 17:01:19,591][02117] Fps is (10 sec: 20480.0, 60 sec: 20343.5, 300 sec: 19925.8). Total num frames: 3387392. Throughput: 0: 5076.7. Samples: 842836. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
329
+ [2025-02-11 17:01:19,593][02117] Avg episode reward: [(0, '27.708')]
330
+ [2025-02-11 17:01:19,595][04717] Saving new best policy, reward=27.708!
331
+ [2025-02-11 17:01:20,180][04730] Updated weights for policy 0, policy_version 830 (0.0012)
332
+ [2025-02-11 17:01:22,264][04730] Updated weights for policy 0, policy_version 840 (0.0011)
333
+ [2025-02-11 17:01:24,266][04730] Updated weights for policy 0, policy_version 850 (0.0012)
334
+ [2025-02-11 17:01:24,591][02117] Fps is (10 sec: 20070.0, 60 sec: 20275.1, 300 sec: 19918.2). Total num frames: 3485696. Throughput: 0: 5059.7. Samples: 872776. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
335
+ [2025-02-11 17:01:24,593][02117] Avg episode reward: [(0, '25.521')]
336
+ [2025-02-11 17:01:26,427][04730] Updated weights for policy 0, policy_version 860 (0.0012)
337
+ [2025-02-11 17:01:28,447][04730] Updated weights for policy 0, policy_version 870 (0.0011)
338
+ [2025-02-11 17:01:29,591][02117] Fps is (10 sec: 19661.0, 60 sec: 20206.9, 300 sec: 19911.1). Total num frames: 3584000. Throughput: 0: 5047.8. Samples: 887138. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
339
+ [2025-02-11 17:01:29,593][02117] Avg episode reward: [(0, '25.614')]
340
+ [2025-02-11 17:01:30,456][04730] Updated weights for policy 0, policy_version 880 (0.0012)
341
+ [2025-02-11 17:01:32,555][04730] Updated weights for policy 0, policy_version 890 (0.0012)
342
+ [2025-02-11 17:01:34,591][02117] Fps is (10 sec: 19661.1, 60 sec: 20138.6, 300 sec: 19904.3). Total num frames: 3682304. Throughput: 0: 5029.0. Samples: 916984. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
343
+ [2025-02-11 17:01:34,593][02117] Avg episode reward: [(0, '23.923')]
344
+ [2025-02-11 17:01:34,633][04730] Updated weights for policy 0, policy_version 900 (0.0012)
345
+ [2025-02-11 17:01:36,609][04730] Updated weights for policy 0, policy_version 910 (0.0011)
346
+ [2025-02-11 17:01:38,610][04730] Updated weights for policy 0, policy_version 920 (0.0011)
347
+ [2025-02-11 17:01:39,591][02117] Fps is (10 sec: 20070.4, 60 sec: 20138.7, 300 sec: 19919.5). Total num frames: 3784704. Throughput: 0: 5037.4. Samples: 947850. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0)
348
+ [2025-02-11 17:01:39,593][02117] Avg episode reward: [(0, '26.635')]
349
+ [2025-02-11 17:01:40,626][04730] Updated weights for policy 0, policy_version 930 (0.0011)
350
+ [2025-02-11 17:01:42,596][04730] Updated weights for policy 0, policy_version 940 (0.0011)
351
+ [2025-02-11 17:01:44,591][02117] Fps is (10 sec: 20480.0, 60 sec: 20207.0, 300 sec: 19933.9). Total num frames: 3887104. Throughput: 0: 5045.2. Samples: 963288. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0)
352
+ [2025-02-11 17:01:44,593][02117] Avg episode reward: [(0, '27.553')]
353
+ [2025-02-11 17:01:44,633][04730] Updated weights for policy 0, policy_version 950 (0.0011)
354
+ [2025-02-11 17:01:46,770][04730] Updated weights for policy 0, policy_version 960 (0.0012)
355
+ [2025-02-11 17:01:48,767][04730] Updated weights for policy 0, policy_version 970 (0.0011)
356
+ [2025-02-11 17:01:49,591][02117] Fps is (10 sec: 20479.8, 60 sec: 20206.9, 300 sec: 19947.5). Total num frames: 3989504. Throughput: 0: 5022.9. Samples: 993200. Policy #0 lag: (min: 0.0, avg: 0.9, max: 2.0)
357
+ [2025-02-11 17:01:49,593][02117] Avg episode reward: [(0, '22.304')]
358
+ [2025-02-11 17:01:50,333][04717] Stopping Batcher_0...
359
+ [2025-02-11 17:01:50,333][04717] Loop batcher_evt_loop terminating...
360
+ [2025-02-11 17:01:50,333][04717] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000978_4005888.pth...
361
+ [2025-02-11 17:01:50,334][02117] Component Batcher_0 stopped!
362
+ [2025-02-11 17:01:50,353][04730] Weights refcount: 2 0
363
+ [2025-02-11 17:01:50,355][04730] Stopping InferenceWorker_p0-w0...
364
+ [2025-02-11 17:01:50,356][04730] Loop inference_proc0-0_evt_loop terminating...
365
+ [2025-02-11 17:01:50,355][02117] Component InferenceWorker_p0-w0 stopped!
366
+ [2025-02-11 17:01:50,377][04738] Stopping RolloutWorker_w7...
367
+ [2025-02-11 17:01:50,378][04738] Loop rollout_proc7_evt_loop terminating...
368
+ [2025-02-11 17:01:50,379][04735] Stopping RolloutWorker_w4...
369
+ [2025-02-11 17:01:50,377][02117] Component RolloutWorker_w7 stopped!
370
+ [2025-02-11 17:01:50,380][04735] Loop rollout_proc4_evt_loop terminating...
371
+ [2025-02-11 17:01:50,381][04733] Stopping RolloutWorker_w2...
372
+ [2025-02-11 17:01:50,382][04733] Loop rollout_proc2_evt_loop terminating...
373
+ [2025-02-11 17:01:50,382][04736] Stopping RolloutWorker_w5...
374
+ [2025-02-11 17:01:50,382][04736] Loop rollout_proc5_evt_loop terminating...
375
+ [2025-02-11 17:01:50,380][02117] Component RolloutWorker_w4 stopped!
376
+ [2025-02-11 17:01:50,384][04731] Stopping RolloutWorker_w1...
377
+ [2025-02-11 17:01:50,385][04734] Stopping RolloutWorker_w3...
378
+ [2025-02-11 17:01:50,385][04731] Loop rollout_proc1_evt_loop terminating...
379
+ [2025-02-11 17:01:50,385][04737] Stopping RolloutWorker_w6...
380
+ [2025-02-11 17:01:50,385][04732] Stopping RolloutWorker_w0...
381
+ [2025-02-11 17:01:50,385][04737] Loop rollout_proc6_evt_loop terminating...
382
+ [2025-02-11 17:01:50,384][02117] Component RolloutWorker_w2 stopped!
383
+ [2025-02-11 17:01:50,385][04732] Loop rollout_proc0_evt_loop terminating...
384
+ [2025-02-11 17:01:50,385][04734] Loop rollout_proc3_evt_loop terminating...
385
+ [2025-02-11 17:01:50,386][02117] Component RolloutWorker_w5 stopped!
386
+ [2025-02-11 17:01:50,388][02117] Component RolloutWorker_w1 stopped!
387
+ [2025-02-11 17:01:50,390][02117] Component RolloutWorker_w3 stopped!
388
+ [2025-02-11 17:01:50,391][02117] Component RolloutWorker_w6 stopped!
389
+ [2025-02-11 17:01:50,392][02117] Component RolloutWorker_w0 stopped!
390
+ [2025-02-11 17:01:50,408][04717] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000978_4005888.pth...
391
+ [2025-02-11 17:01:50,508][04717] Stopping LearnerWorker_p0...
392
+ [2025-02-11 17:01:50,509][04717] Loop learner_proc0_evt_loop terminating...
393
+ [2025-02-11 17:01:50,510][02117] Component LearnerWorker_p0 stopped!
394
+ [2025-02-11 17:01:50,513][02117] Waiting for process learner_proc0 to stop...
395
+ [2025-02-11 17:01:51,471][02117] Waiting for process inference_proc0-0 to join...
396
+ [2025-02-11 17:01:51,473][02117] Waiting for process rollout_proc0 to join...
397
+ [2025-02-11 17:01:51,475][02117] Waiting for process rollout_proc1 to join...
398
+ [2025-02-11 17:01:51,476][02117] Waiting for process rollout_proc2 to join...
399
+ [2025-02-11 17:01:51,478][02117] Waiting for process rollout_proc3 to join...
400
+ [2025-02-11 17:01:51,479][02117] Waiting for process rollout_proc4 to join...
401
+ [2025-02-11 17:01:51,480][02117] Waiting for process rollout_proc5 to join...
402
+ [2025-02-11 17:01:51,482][02117] Waiting for process rollout_proc6 to join...
403
+ [2025-02-11 17:01:51,484][02117] Waiting for process rollout_proc7 to join...
404
+ [2025-02-11 17:01:51,485][02117] Batcher 0 profile tree view:
405
+ batching: 11.8391, releasing_batches: 0.0239
406
+ [2025-02-11 17:01:51,487][02117] InferenceWorker_p0-w0 profile tree view:
407
+ wait_policy: 0.0001
408
+ wait_policy_total: 3.8509
409
+ update_model: 3.2577
410
+ weight_update: 0.0012
411
+ one_step: 0.0028
412
+ handle_policy_step: 186.2668
413
+ deserialize: 7.5123, stack: 1.2923, obs_to_device_normalize: 46.5476, forward: 87.7695, send_messages: 12.9137
414
+ prepare_outputs: 23.0564
415
+ to_cpu: 14.8538
416
+ [2025-02-11 17:01:51,488][02117] Learner 0 profile tree view:
417
+ misc: 0.0037, prepare_batch: 9.7542
418
+ train: 23.1544
419
+ epoch_init: 0.0043, minibatch_init: 0.0055, losses_postprocess: 0.2719, kl_divergence: 0.3588, after_optimizer: 5.1615
420
+ calculate_losses: 9.5406
421
+ losses_init: 0.0032, forward_head: 0.6877, bptt_initial: 5.7729, tail: 0.5934, advantages_returns: 0.1634, losses: 1.1112
422
+ bptt: 1.0598
423
+ bptt_forward_core: 1.0099
424
+ update: 7.4917
425
+ clip: 0.7795
426
+ [2025-02-11 17:01:51,489][02117] RolloutWorker_w0 profile tree view:
427
+ wait_for_trajectories: 0.1244, enqueue_policy_requests: 8.8805, env_step: 128.7927, overhead: 5.5858, complete_rollouts: 0.2136
428
+ save_policy_outputs: 7.9403
429
+ split_output_tensors: 3.0252
430
+ [2025-02-11 17:01:51,490][02117] RolloutWorker_w7 profile tree view:
431
+ wait_for_trajectories: 0.1250, enqueue_policy_requests: 8.8758, env_step: 128.8295, overhead: 5.5466, complete_rollouts: 0.2104
432
+ save_policy_outputs: 7.9921
433
+ split_output_tensors: 3.0659
434
+ [2025-02-11 17:01:51,493][02117] Loop Runner_EvtLoop terminating...
435
+ [2025-02-11 17:01:51,494][02117] Runner profile tree view:
436
+ main_loop: 212.2128
437
+ [2025-02-11 17:01:51,495][02117] Collected {0: 4005888}, FPS: 18876.7
438
+ [2025-02-11 17:02:12,715][02117] Loading existing experiment configuration from /content/train_dir/default_experiment/config.json
439
+ [2025-02-11 17:02:12,717][02117] Overriding arg 'num_workers' with value 1 passed from command line
440
+ [2025-02-11 17:02:12,718][02117] Adding new argument 'no_render'=True that is not in the saved config file!
441
+ [2025-02-11 17:02:12,720][02117] Adding new argument 'save_video'=True that is not in the saved config file!
442
+ [2025-02-11 17:02:12,721][02117] Adding new argument 'video_frames'=1000000000.0 that is not in the saved config file!
443
+ [2025-02-11 17:02:12,722][02117] Adding new argument 'video_name'=None that is not in the saved config file!
444
+ [2025-02-11 17:02:12,723][02117] Adding new argument 'max_num_frames'=1000000000.0 that is not in the saved config file!
445
+ [2025-02-11 17:02:12,725][02117] Adding new argument 'max_num_episodes'=10 that is not in the saved config file!
446
+ [2025-02-11 17:02:12,726][02117] Adding new argument 'push_to_hub'=False that is not in the saved config file!
447
+ [2025-02-11 17:02:12,727][02117] Adding new argument 'hf_repository'=None that is not in the saved config file!
448
+ [2025-02-11 17:02:12,728][02117] Adding new argument 'policy_index'=0 that is not in the saved config file!
449
+ [2025-02-11 17:02:12,730][02117] Adding new argument 'eval_deterministic'=False that is not in the saved config file!
450
+ [2025-02-11 17:02:12,731][02117] Adding new argument 'train_script'=None that is not in the saved config file!
451
+ [2025-02-11 17:02:12,732][02117] Adding new argument 'enjoy_script'=None that is not in the saved config file!
452
+ [2025-02-11 17:02:12,733][02117] Using frameskip 1 and render_action_repeat=4 for evaluation
453
+ [2025-02-11 17:02:12,762][02117] Doom resolution: 160x120, resize resolution: (128, 72)
454
+ [2025-02-11 17:02:12,765][02117] RunningMeanStd input shape: (3, 72, 128)
455
+ [2025-02-11 17:02:12,767][02117] RunningMeanStd input shape: (1,)
456
+ [2025-02-11 17:02:12,781][02117] ConvEncoder: input_channels=3
457
+ [2025-02-11 17:02:12,886][02117] Conv encoder output size: 512
458
+ [2025-02-11 17:02:12,888][02117] Policy head output size: 512
459
+ [2025-02-11 17:02:13,041][02117] Loading state from checkpoint /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000978_4005888.pth...
460
+ [2025-02-11 17:02:13,854][02117] Num frames 100...
461
+ [2025-02-11 17:02:13,981][02117] Num frames 200...
462
+ [2025-02-11 17:02:14,110][02117] Num frames 300...
463
+ [2025-02-11 17:02:14,237][02117] Num frames 400...
464
+ [2025-02-11 17:02:14,363][02117] Num frames 500...
465
+ [2025-02-11 17:02:14,487][02117] Num frames 600...
466
+ [2025-02-11 17:02:14,617][02117] Num frames 700...
467
+ [2025-02-11 17:02:14,745][02117] Num frames 800...
468
+ [2025-02-11 17:02:14,878][02117] Num frames 900...
469
+ [2025-02-11 17:02:15,015][02117] Num frames 1000...
470
+ [2025-02-11 17:02:15,149][02117] Num frames 1100...
471
+ [2025-02-11 17:02:15,275][02117] Num frames 1200...
472
+ [2025-02-11 17:02:15,402][02117] Num frames 1300...
473
+ [2025-02-11 17:02:15,530][02117] Num frames 1400...
474
+ [2025-02-11 17:02:15,657][02117] Num frames 1500...
475
+ [2025-02-11 17:02:15,784][02117] Num frames 1600...
476
+ [2025-02-11 17:02:15,913][02117] Num frames 1700...
477
+ [2025-02-11 17:02:16,043][02117] Num frames 1800...
478
+ [2025-02-11 17:02:16,208][02117] Avg episode rewards: #0: 47.859, true rewards: #0: 18.860
479
+ [2025-02-11 17:02:16,209][02117] Avg episode reward: 47.859, avg true_objective: 18.860
480
+ [2025-02-11 17:02:16,229][02117] Num frames 1900...
481
+ [2025-02-11 17:02:16,353][02117] Num frames 2000...
482
+ [2025-02-11 17:02:16,479][02117] Num frames 2100...
483
+ [2025-02-11 17:02:16,604][02117] Num frames 2200...
484
+ [2025-02-11 17:02:16,730][02117] Num frames 2300...
485
+ [2025-02-11 17:02:16,855][02117] Num frames 2400...
486
+ [2025-02-11 17:02:16,982][02117] Num frames 2500...
487
+ [2025-02-11 17:02:17,109][02117] Num frames 2600...
488
+ [2025-02-11 17:02:17,236][02117] Num frames 2700...
489
+ [2025-02-11 17:02:17,314][02117] Avg episode rewards: #0: 31.590, true rewards: #0: 13.590
490
+ [2025-02-11 17:02:17,315][02117] Avg episode reward: 31.590, avg true_objective: 13.590
491
+ [2025-02-11 17:02:17,420][02117] Num frames 2800...
492
+ [2025-02-11 17:02:17,547][02117] Num frames 2900...
493
+ [2025-02-11 17:02:17,674][02117] Num frames 3000...
494
+ [2025-02-11 17:02:17,800][02117] Num frames 3100...
495
+ [2025-02-11 17:02:17,928][02117] Num frames 3200...
496
+ [2025-02-11 17:02:18,058][02117] Num frames 3300...
497
+ [2025-02-11 17:02:18,185][02117] Num frames 3400...
498
+ [2025-02-11 17:02:18,311][02117] Num frames 3500...
499
+ [2025-02-11 17:02:18,440][02117] Num frames 3600...
500
+ [2025-02-11 17:02:18,567][02117] Num frames 3700...
501
+ [2025-02-11 17:02:18,697][02117] Num frames 3800...
502
+ [2025-02-11 17:02:18,827][02117] Num frames 3900...
503
+ [2025-02-11 17:02:18,955][02117] Num frames 4000...
504
+ [2025-02-11 17:02:19,090][02117] Num frames 4100...
505
+ [2025-02-11 17:02:19,224][02117] Num frames 4200...
506
+ [2025-02-11 17:02:19,353][02117] Num frames 4300...
507
+ [2025-02-11 17:02:19,479][02117] Num frames 4400...
508
+ [2025-02-11 17:02:19,611][02117] Num frames 4500...
509
+ [2025-02-11 17:02:19,741][02117] Num frames 4600...
510
+ [2025-02-11 17:02:19,872][02117] Num frames 4700...
511
+ [2025-02-11 17:02:20,012][02117] Num frames 4800...
512
+ [2025-02-11 17:02:20,093][02117] Avg episode rewards: #0: 41.059, true rewards: #0: 16.060
513
+ [2025-02-11 17:02:20,094][02117] Avg episode reward: 41.059, avg true_objective: 16.060
514
+ [2025-02-11 17:02:20,205][02117] Num frames 4900...
515
+ [2025-02-11 17:02:20,338][02117] Num frames 5000...
516
+ [2025-02-11 17:02:20,467][02117] Num frames 5100...
517
+ [2025-02-11 17:02:20,594][02117] Num frames 5200...
518
+ [2025-02-11 17:02:20,719][02117] Num frames 5300...
519
+ [2025-02-11 17:02:20,847][02117] Num frames 5400...
520
+ [2025-02-11 17:02:20,936][02117] Avg episode rewards: #0: 34.065, true rewards: #0: 13.565
521
+ [2025-02-11 17:02:20,937][02117] Avg episode reward: 34.065, avg true_objective: 13.565
522
+ [2025-02-11 17:02:21,032][02117] Num frames 5500...
523
+ [2025-02-11 17:02:21,160][02117] Num frames 5600...
524
+ [2025-02-11 17:02:21,288][02117] Num frames 5700...
525
+ [2025-02-11 17:02:21,413][02117] Num frames 5800...
526
+ [2025-02-11 17:02:21,539][02117] Num frames 5900...
527
+ [2025-02-11 17:02:21,707][02117] Avg episode rewards: #0: 29.584, true rewards: #0: 11.984
528
+ [2025-02-11 17:02:21,709][02117] Avg episode reward: 29.584, avg true_objective: 11.984
529
+ [2025-02-11 17:02:21,721][02117] Num frames 6000...
530
+ [2025-02-11 17:02:21,849][02117] Num frames 6100...
531
+ [2025-02-11 17:02:21,983][02117] Num frames 6200...
532
+ [2025-02-11 17:02:22,115][02117] Num frames 6300...
533
+ [2025-02-11 17:02:22,245][02117] Num frames 6400...
534
+ [2025-02-11 17:02:22,373][02117] Num frames 6500...
535
+ [2025-02-11 17:02:22,500][02117] Num frames 6600...
536
+ [2025-02-11 17:02:22,629][02117] Num frames 6700...
537
+ [2025-02-11 17:02:22,756][02117] Num frames 6800...
538
+ [2025-02-11 17:02:22,886][02117] Num frames 6900...
539
+ [2025-02-11 17:02:23,019][02117] Num frames 7000...
540
+ [2025-02-11 17:02:23,148][02117] Num frames 7100...
541
+ [2025-02-11 17:02:23,301][02117] Avg episode rewards: #0: 29.460, true rewards: #0: 11.960
542
+ [2025-02-11 17:02:23,303][02117] Avg episode reward: 29.460, avg true_objective: 11.960
543
+ [2025-02-11 17:02:23,336][02117] Num frames 7200...
544
+ [2025-02-11 17:02:23,461][02117] Num frames 7300...
545
+ [2025-02-11 17:02:23,588][02117] Num frames 7400...
546
+ [2025-02-11 17:02:23,713][02117] Num frames 7500...
547
+ [2025-02-11 17:02:23,842][02117] Num frames 7600...
548
+ [2025-02-11 17:02:23,973][02117] Num frames 7700...
549
+ [2025-02-11 17:02:24,102][02117] Num frames 7800...
550
+ [2025-02-11 17:02:24,230][02117] Num frames 7900...
551
+ [2025-02-11 17:02:24,355][02117] Num frames 8000...
552
+ [2025-02-11 17:02:24,481][02117] Num frames 8100...
553
+ [2025-02-11 17:02:24,610][02117] Num frames 8200...
554
+ [2025-02-11 17:02:24,738][02117] Num frames 8300...
555
+ [2025-02-11 17:02:24,863][02117] Num frames 8400...
556
+ [2025-02-11 17:02:24,995][02117] Num frames 8500...
557
+ [2025-02-11 17:02:25,124][02117] Num frames 8600...
558
+ [2025-02-11 17:02:25,253][02117] Num frames 8700...
559
+ [2025-02-11 17:02:25,324][02117] Avg episode rewards: #0: 30.303, true rewards: #0: 12.446
560
+ [2025-02-11 17:02:25,325][02117] Avg episode reward: 30.303, avg true_objective: 12.446
561
+ [2025-02-11 17:02:25,436][02117] Num frames 8800...
562
+ [2025-02-11 17:02:25,562][02117] Num frames 8900...
563
+ [2025-02-11 17:02:25,686][02117] Num frames 9000...
564
+ [2025-02-11 17:02:25,814][02117] Num frames 9100...
565
+ [2025-02-11 17:02:25,941][02117] Num frames 9200...
566
+ [2025-02-11 17:02:26,067][02117] Num frames 9300...
567
+ [2025-02-11 17:02:26,195][02117] Num frames 9400...
568
+ [2025-02-11 17:02:26,324][02117] Num frames 9500...
569
+ [2025-02-11 17:02:26,451][02117] Num frames 9600...
570
+ [2025-02-11 17:02:26,575][02117] Num frames 9700...
571
+ [2025-02-11 17:02:26,705][02117] Num frames 9800...
572
+ [2025-02-11 17:02:26,832][02117] Num frames 9900...
573
+ [2025-02-11 17:02:26,959][02117] Num frames 10000...
574
+ [2025-02-11 17:02:27,089][02117] Num frames 10100...
575
+ [2025-02-11 17:02:27,216][02117] Num frames 10200...
576
+ [2025-02-11 17:02:27,341][02117] Num frames 10300...
577
+ [2025-02-11 17:02:27,470][02117] Num frames 10400...
578
+ [2025-02-11 17:02:27,601][02117] Num frames 10500...
579
+ [2025-02-11 17:02:27,727][02117] Num frames 10600...
580
+ [2025-02-11 17:02:27,856][02117] Num frames 10700...
581
+ [2025-02-11 17:02:27,991][02117] Avg episode rewards: #0: 33.453, true rewards: #0: 13.454
582
+ [2025-02-11 17:02:27,993][02117] Avg episode reward: 33.453, avg true_objective: 13.454
583
+ [2025-02-11 17:02:28,046][02117] Num frames 10800...
584
+ [2025-02-11 17:02:28,173][02117] Num frames 10900...
585
+ [2025-02-11 17:02:28,299][02117] Num frames 11000...
586
+ [2025-02-11 17:02:28,426][02117] Num frames 11100...
587
+ [2025-02-11 17:02:28,549][02117] Num frames 11200...
588
+ [2025-02-11 17:02:28,676][02117] Num frames 11300...
589
+ [2025-02-11 17:02:28,802][02117] Num frames 11400...
590
+ [2025-02-11 17:02:28,941][02117] Avg episode rewards: #0: 31.296, true rewards: #0: 12.741
591
+ [2025-02-11 17:02:28,942][02117] Avg episode reward: 31.296, avg true_objective: 12.741
592
+ [2025-02-11 17:02:28,986][02117] Num frames 11500...
593
+ [2025-02-11 17:02:29,117][02117] Num frames 11600...
594
+ [2025-02-11 17:02:29,242][02117] Num frames 11700...
595
+ [2025-02-11 17:02:29,368][02117] Num frames 11800...
596
+ [2025-02-11 17:02:29,494][02117] Num frames 11900...
597
+ [2025-02-11 17:02:29,621][02117] Num frames 12000...
598
+ [2025-02-11 17:02:29,746][02117] Num frames 12100...
599
+ [2025-02-11 17:02:29,874][02117] Num frames 12200...
600
+ [2025-02-11 17:02:29,993][02117] Avg episode rewards: #0: 29.850, true rewards: #0: 12.250
601
+ [2025-02-11 17:02:29,994][02117] Avg episode reward: 29.850, avg true_objective: 12.250
602
+ [2025-02-11 17:02:59,239][02117] Replay video saved to /content/train_dir/default_experiment/replay.mp4!
603
+ [2025-02-11 17:04:57,900][02117] Loading existing experiment configuration from /content/train_dir/default_experiment/config.json
604
+ [2025-02-11 17:04:57,901][02117] Overriding arg 'num_workers' with value 1 passed from command line
605
+ [2025-02-11 17:04:57,902][02117] Adding new argument 'no_render'=True that is not in the saved config file!
606
+ [2025-02-11 17:04:57,904][02117] Adding new argument 'save_video'=True that is not in the saved config file!
607
+ [2025-02-11 17:04:57,905][02117] Adding new argument 'video_frames'=1000000000.0 that is not in the saved config file!
608
+ [2025-02-11 17:04:57,906][02117] Adding new argument 'video_name'=None that is not in the saved config file!
609
+ [2025-02-11 17:04:57,908][02117] Adding new argument 'max_num_frames'=100000 that is not in the saved config file!
610
+ [2025-02-11 17:04:57,909][02117] Adding new argument 'max_num_episodes'=10 that is not in the saved config file!
611
+ [2025-02-11 17:04:57,910][02117] Adding new argument 'push_to_hub'=True that is not in the saved config file!
612
+ [2025-02-11 17:04:57,912][02117] Adding new argument 'hf_repository'='mjm54/doom_health_gathering_supreme' that is not in the saved config file!
613
+ [2025-02-11 17:04:57,913][02117] Adding new argument 'policy_index'=0 that is not in the saved config file!
614
+ [2025-02-11 17:04:57,914][02117] Adding new argument 'eval_deterministic'=False that is not in the saved config file!
615
+ [2025-02-11 17:04:57,915][02117] Adding new argument 'train_script'=None that is not in the saved config file!
616
+ [2025-02-11 17:04:57,917][02117] Adding new argument 'enjoy_script'=None that is not in the saved config file!
617
+ [2025-02-11 17:04:57,918][02117] Using frameskip 1 and render_action_repeat=4 for evaluation
618
+ [2025-02-11 17:04:57,942][02117] RunningMeanStd input shape: (3, 72, 128)
619
+ [2025-02-11 17:04:57,945][02117] RunningMeanStd input shape: (1,)
620
+ [2025-02-11 17:04:57,956][02117] ConvEncoder: input_channels=3
621
+ [2025-02-11 17:04:57,993][02117] Conv encoder output size: 512
622
+ [2025-02-11 17:04:57,995][02117] Policy head output size: 512
623
+ [2025-02-11 17:04:58,017][02117] Loading state from checkpoint /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000978_4005888.pth...
624
+ [2025-02-11 17:04:58,455][02117] Num frames 100...
625
+ [2025-02-11 17:04:58,579][02117] Num frames 200...
626
+ [2025-02-11 17:04:58,703][02117] Num frames 300...
627
+ [2025-02-11 17:04:58,829][02117] Num frames 400...
628
+ [2025-02-11 17:04:58,964][02117] Num frames 500...
629
+ [2025-02-11 17:04:59,100][02117] Num frames 600...
630
+ [2025-02-11 17:04:59,234][02117] Num frames 700...
631
+ [2025-02-11 17:04:59,368][02117] Num frames 800...
632
+ [2025-02-11 17:04:59,504][02117] Num frames 900...
633
+ [2025-02-11 17:04:59,636][02117] Num frames 1000...
634
+ [2025-02-11 17:04:59,768][02117] Num frames 1100...
635
+ [2025-02-11 17:04:59,906][02117] Num frames 1200...
636
+ [2025-02-11 17:05:00,038][02117] Num frames 1300...
637
+ [2025-02-11 17:05:00,165][02117] Num frames 1400...
638
+ [2025-02-11 17:05:00,296][02117] Num frames 1500...
639
+ [2025-02-11 17:05:00,423][02117] Num frames 1600...
640
+ [2025-02-11 17:05:00,491][02117] Avg episode rewards: #0: 35.090, true rewards: #0: 16.090
641
+ [2025-02-11 17:05:00,492][02117] Avg episode reward: 35.090, avg true_objective: 16.090
642
+ [2025-02-11 17:05:00,604][02117] Num frames 1700...
643
+ [2025-02-11 17:05:00,730][02117] Num frames 1800...
644
+ [2025-02-11 17:05:00,855][02117] Num frames 1900...
645
+ [2025-02-11 17:05:00,979][02117] Num frames 2000...
646
+ [2025-02-11 17:05:01,106][02117] Num frames 2100...
647
+ [2025-02-11 17:05:01,231][02117] Num frames 2200...
648
+ [2025-02-11 17:05:01,357][02117] Num frames 2300...
649
+ [2025-02-11 17:05:01,507][02117] Avg episode rewards: #0: 25.880, true rewards: #0: 11.880
650
+ [2025-02-11 17:05:01,508][02117] Avg episode reward: 25.880, avg true_objective: 11.880
651
+ [2025-02-11 17:05:01,539][02117] Num frames 2400...
652
+ [2025-02-11 17:05:01,666][02117] Num frames 2500...
653
+ [2025-02-11 17:05:01,794][02117] Num frames 2600...
654
+ [2025-02-11 17:05:01,921][02117] Num frames 2700...
655
+ [2025-02-11 17:05:02,050][02117] Num frames 2800...
656
+ [2025-02-11 17:05:02,175][02117] Num frames 2900...
657
+ [2025-02-11 17:05:02,301][02117] Num frames 3000...
658
+ [2025-02-11 17:05:02,428][02117] Num frames 3100...
659
+ [2025-02-11 17:05:02,552][02117] Num frames 3200...
660
+ [2025-02-11 17:05:02,618][02117] Avg episode rewards: #0: 23.360, true rewards: #0: 10.693
661
+ [2025-02-11 17:05:02,619][02117] Avg episode reward: 23.360, avg true_objective: 10.693
662
+ [2025-02-11 17:05:02,734][02117] Num frames 3300...
663
+ [2025-02-11 17:05:02,859][02117] Num frames 3400...
664
+ [2025-02-11 17:05:02,985][02117] Num frames 3500...
665
+ [2025-02-11 17:05:03,110][02117] Num frames 3600...
666
+ [2025-02-11 17:05:03,236][02117] Num frames 3700...
667
+ [2025-02-11 17:05:03,363][02117] Num frames 3800...
668
+ [2025-02-11 17:05:03,488][02117] Num frames 3900...
669
+ [2025-02-11 17:05:03,612][02117] Num frames 4000...
670
+ [2025-02-11 17:05:03,739][02117] Num frames 4100...
671
+ [2025-02-11 17:05:03,865][02117] Num frames 4200...
672
+ [2025-02-11 17:05:03,993][02117] Num frames 4300...
673
+ [2025-02-11 17:05:04,120][02117] Num frames 4400...
674
+ [2025-02-11 17:05:04,247][02117] Num frames 4500...
675
+ [2025-02-11 17:05:04,327][02117] Avg episode rewards: #0: 26.300, true rewards: #0: 11.300
676
+ [2025-02-11 17:05:04,329][02117] Avg episode reward: 26.300, avg true_objective: 11.300
677
+ [2025-02-11 17:05:04,433][02117] Num frames 4600...
678
+ [2025-02-11 17:05:04,558][02117] Num frames 4700...
679
+ [2025-02-11 17:05:04,684][02117] Num frames 4800...
680
+ [2025-02-11 17:05:04,808][02117] Num frames 4900...
681
+ [2025-02-11 17:05:04,934][02117] Num frames 5000...
682
+ [2025-02-11 17:05:05,064][02117] Num frames 5100...
683
+ [2025-02-11 17:05:05,189][02117] Num frames 5200...
684
+ [2025-02-11 17:05:05,316][02117] Num frames 5300...
685
+ [2025-02-11 17:05:05,445][02117] Num frames 5400...
686
+ [2025-02-11 17:05:05,572][02117] Num frames 5500...
687
+ [2025-02-11 17:05:05,699][02117] Num frames 5600...
688
+ [2025-02-11 17:05:05,765][02117] Avg episode rewards: #0: 26.016, true rewards: #0: 11.216
689
+ [2025-02-11 17:05:05,766][02117] Avg episode reward: 26.016, avg true_objective: 11.216
690
+ [2025-02-11 17:05:05,881][02117] Num frames 5700...
691
+ [2025-02-11 17:05:06,004][02117] Num frames 5800...
692
+ [2025-02-11 17:05:06,129][02117] Num frames 5900...
693
+ [2025-02-11 17:05:06,255][02117] Num frames 6000...
694
+ [2025-02-11 17:05:06,379][02117] Num frames 6100...
695
+ [2025-02-11 17:05:06,506][02117] Num frames 6200...
696
+ [2025-02-11 17:05:06,633][02117] Num frames 6300...
697
+ [2025-02-11 17:05:06,758][02117] Num frames 6400...
698
+ [2025-02-11 17:05:06,885][02117] Num frames 6500...
699
+ [2025-02-11 17:05:07,017][02117] Num frames 6600...
700
+ [2025-02-11 17:05:07,145][02117] Num frames 6700...
701
+ [2025-02-11 17:05:07,271][02117] Num frames 6800...
702
+ [2025-02-11 17:05:07,401][02117] Num frames 6900...
703
+ [2025-02-11 17:05:07,529][02117] Num frames 7000...
704
+ [2025-02-11 17:05:07,660][02117] Num frames 7100...
705
+ [2025-02-11 17:05:07,787][02117] Num frames 7200...
706
+ [2025-02-11 17:05:07,913][02117] Num frames 7300...
707
+ [2025-02-11 17:05:08,043][02117] Num frames 7400...
708
+ [2025-02-11 17:05:08,174][02117] Num frames 7500...
709
+ [2025-02-11 17:05:08,300][02117] Num frames 7600...
710
+ [2025-02-11 17:05:08,427][02117] Num frames 7700...
711
+ [2025-02-11 17:05:08,492][02117] Avg episode rewards: #0: 31.180, true rewards: #0: 12.847
712
+ [2025-02-11 17:05:08,493][02117] Avg episode reward: 31.180, avg true_objective: 12.847
713
+ [2025-02-11 17:05:08,610][02117] Num frames 7800...
714
+ [2025-02-11 17:05:08,735][02117] Num frames 7900...
715
+ [2025-02-11 17:05:08,857][02117] Num frames 8000...
716
+ [2025-02-11 17:05:08,983][02117] Num frames 8100...
717
+ [2025-02-11 17:05:09,114][02117] Num frames 8200...
718
+ [2025-02-11 17:05:09,240][02117] Num frames 8300...
719
+ [2025-02-11 17:05:09,367][02117] Num frames 8400...
720
+ [2025-02-11 17:05:09,493][02117] Num frames 8500...
721
+ [2025-02-11 17:05:09,624][02117] Num frames 8600...
722
+ [2025-02-11 17:05:09,750][02117] Num frames 8700...
723
+ [2025-02-11 17:05:09,878][02117] Num frames 8800...
724
+ [2025-02-11 17:05:10,006][02117] Num frames 8900...
725
+ [2025-02-11 17:05:10,133][02117] Num frames 9000...
726
+ [2025-02-11 17:05:10,259][02117] Num frames 9100...
727
+ [2025-02-11 17:05:10,398][02117] Num frames 9200...
728
+ [2025-02-11 17:05:10,526][02117] Num frames 9300...
729
+ [2025-02-11 17:05:10,653][02117] Num frames 9400...
730
+ [2025-02-11 17:05:10,782][02117] Num frames 9500...
731
+ [2025-02-11 17:05:10,911][02117] Num frames 9600...
732
+ [2025-02-11 17:05:11,002][02117] Avg episode rewards: #0: 33.326, true rewards: #0: 13.754
733
+ [2025-02-11 17:05:11,003][02117] Avg episode reward: 33.326, avg true_objective: 13.754
734
+ [2025-02-11 17:05:11,097][02117] Num frames 9700...
735
+ [2025-02-11 17:05:11,233][02117] Num frames 9800...
736
+ [2025-02-11 17:05:11,369][02117] Num frames 9900...
737
+ [2025-02-11 17:05:11,508][02117] Num frames 10000...
738
+ [2025-02-11 17:05:11,647][02117] Num frames 10100...
739
+ [2025-02-11 17:05:11,779][02117] Num frames 10200...
740
+ [2025-02-11 17:05:11,906][02117] Num frames 10300...
741
+ [2025-02-11 17:05:12,035][02117] Num frames 10400...
742
+ [2025-02-11 17:05:12,160][02117] Num frames 10500...
743
+ [2025-02-11 17:05:12,289][02117] Num frames 10600...
744
+ [2025-02-11 17:05:12,383][02117] Avg episode rewards: #0: 32.164, true rewards: #0: 13.289
745
+ [2025-02-11 17:05:12,385][02117] Avg episode reward: 32.164, avg true_objective: 13.289
746
+ [2025-02-11 17:05:12,472][02117] Num frames 10700...
747
+ [2025-02-11 17:05:12,601][02117] Num frames 10800...
748
+ [2025-02-11 17:05:12,727][02117] Num frames 10900...
749
+ [2025-02-11 17:05:12,854][02117] Num frames 11000...
750
+ [2025-02-11 17:05:12,981][02117] Num frames 11100...
751
+ [2025-02-11 17:05:13,112][02117] Num frames 11200...
752
+ [2025-02-11 17:05:13,238][02117] Num frames 11300...
753
+ [2025-02-11 17:05:13,364][02117] Num frames 11400...
754
+ [2025-02-11 17:05:13,492][02117] Num frames 11500...
755
+ [2025-02-11 17:05:13,621][02117] Num frames 11600...
756
+ [2025-02-11 17:05:13,747][02117] Num frames 11700...
757
+ [2025-02-11 17:05:13,874][02117] Num frames 11800...
758
+ [2025-02-11 17:05:14,015][02117] Num frames 11900...
759
+ [2025-02-11 17:05:14,149][02117] Num frames 12000...
760
+ [2025-02-11 17:05:14,288][02117] Num frames 12100...
761
+ [2025-02-11 17:05:14,423][02117] Num frames 12200...
762
+ [2025-02-11 17:05:14,524][02117] Avg episode rewards: #0: 32.929, true rewards: #0: 13.596
763
+ [2025-02-11 17:05:14,526][02117] Avg episode reward: 32.929, avg true_objective: 13.596
764
+ [2025-02-11 17:05:14,607][02117] Num frames 12300...
765
+ [2025-02-11 17:05:14,735][02117] Num frames 12400...
766
+ [2025-02-11 17:05:14,867][02117] Num frames 12500...
767
+ [2025-02-11 17:05:15,000][02117] Num frames 12600...
768
+ [2025-02-11 17:05:15,131][02117] Num frames 12700...
769
+ [2025-02-11 17:05:15,261][02117] Num frames 12800...
770
+ [2025-02-11 17:05:15,390][02117] Num frames 12900...
771
+ [2025-02-11 17:05:15,515][02117] Num frames 13000...
772
+ [2025-02-11 17:05:15,643][02117] Num frames 13100...
773
+ [2025-02-11 17:05:15,776][02117] Num frames 13200...
774
+ [2025-02-11 17:05:15,906][02117] Num frames 13300...
775
+ [2025-02-11 17:05:16,034][02117] Num frames 13400...
776
+ [2025-02-11 17:05:16,163][02117] Num frames 13500...
777
+ [2025-02-11 17:05:16,292][02117] Num frames 13600...
778
+ [2025-02-11 17:05:16,420][02117] Num frames 13700...
779
+ [2025-02-11 17:05:16,549][02117] Num frames 13800...
780
+ [2025-02-11 17:05:16,719][02117] Avg episode rewards: #0: 34.187, true rewards: #0: 13.887
781
+ [2025-02-11 17:05:16,721][02117] Avg episode reward: 34.187, avg true_objective: 13.887
782
+ [2025-02-11 17:05:49,668][02117] Replay video saved to /content/train_dir/default_experiment/replay.mp4!