Hugging Face's logo

51nd0re1
/
poca-SoccerTwos

Reinforcement Learning
ml-agents
TensorBoard
ONNX
SoccerTwos
deep-reinforcement-learning
ML-Agents-SoccerTwos
Model card Files Metrics Community
51nd0re1 commited on
Commit
c1e7a87
·
verified ·
1 Parent(s): 44dbcc6

First Push`

Browse files
Files changed (27) hide show
  1. README.md +35 -0
  2. SoccerTwos.onnx +3 -0
  3. SoccerTwos/SoccerTwos-0.pt +3 -0
  4. SoccerTwos/SoccerTwos-100000009.onnx +3 -0
  5. SoccerTwos/SoccerTwos-100000009.pt +3 -0
  6. SoccerTwos/SoccerTwos-110522.onnx +3 -0
  7. SoccerTwos/SoccerTwos-110522.pt +3 -0
  8. SoccerTwos/SoccerTwos-98499983.onnx +3 -0
  9. SoccerTwos/SoccerTwos-98499983.pt +3 -0
  10. SoccerTwos/SoccerTwos-98999986.onnx +3 -0
  11. SoccerTwos/SoccerTwos-98999986.pt +3 -0
  12. SoccerTwos/SoccerTwos-99499947.onnx +3 -0
  13. SoccerTwos/SoccerTwos-99499947.pt +3 -0
  14. SoccerTwos/SoccerTwos-99999997.onnx +3 -0
  15. SoccerTwos/SoccerTwos-99999997.pt +3 -0
  16. SoccerTwos/checkpoint.pt +3 -0
  17. SoccerTwos/events.out.tfevents.1738646548.tesla03.5092.0 +3 -0
  18. SoccerTwos/events.out.tfevents.1738646627.tesla03.5457.0 +3 -0
  19. SoccerTwos/events.out.tfevents.1738646947.tesla03.5870.0 +3 -0
  20. SoccerTwos/events.out.tfevents.1738647027.tesla03.6546.0 +3 -0
  21. SoccerTwos/events.out.tfevents.1738647259.tesla03.6944.0 +3 -0
  22. SoccerTwos/events.out.tfevents.1738647345.tesla03.7360.0 +3 -0
  23. config.json +1 -0
  24. configuration.yaml +84 -0
  25. run_logs/Player-0.log +0 -0
  26. run_logs/timers.json +424 -0
  27. run_logs/training_status.json +66 -0
README.md ADDED
@@ -0,0 +1,35 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: ml-agents
3
+ tags:
4
+ - SoccerTwos
5
+ - deep-reinforcement-learning
6
+ - reinforcement-learning
7
+ - ML-Agents-SoccerTwos
8
+ ---
9
+
10
+ # **poca** Agent playing **SoccerTwos**
11
+ This is a trained model of a **poca** agent playing **SoccerTwos**
12
+ using the [Unity ML-Agents Library](https://github.com/Unity-Technologies/ml-agents).
13
+
14
+ ## Usage (with ML-Agents)
15
+ The Documentation: https://unity-technologies.github.io/ml-agents/ML-Agents-Toolkit-Documentation/
16
+
17
+ We wrote a complete tutorial to learn to train your first agent using ML-Agents and publish it to the Hub:
18
+ - A *short tutorial* where you teach Huggy the Dog 🐶 to fetch the stick and then play with him directly in your
19
+ browser: https://huggingface.co/learn/deep-rl-course/unitbonus1/introduction
20
+ - A *longer tutorial* to understand how works ML-Agents:
21
+ https://huggingface.co/learn/deep-rl-course/unit5/introduction
22
+
23
+ ### Resume the training
24
+ ```bash
25
+ mlagents-learn <your_configuration_file_path.yaml> --run-id=<run_id> --resume
26
+ ```
27
+
28
+ ### Watch your Agent play
29
+ You can watch your agent **playing directly in your browser**
30
+
31
+ 1. If the environment is part of ML-Agents official environments, go to https://huggingface.co/unity
32
+ 2. Step 1: Find your model_id: 51nd0re1/poca-SoccerTwos
33
+ 3. Step 2: Select your *.nn /*.onnx file
34
+ 4. Click on Watch the agent play 👀
35
+
SoccerTwos.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:872aa75fa12b10601f59935f85b09587f2cbb58d7e6ef79a6c318651b819715e
3
+ size 1768747
SoccerTwos/SoccerTwos-0.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1eb8bfacdd9424429edaf23a4b63e697db9818dfd33f1d4ed8fd603491198389
3
+ size 9479282
SoccerTwos/SoccerTwos-100000009.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:872aa75fa12b10601f59935f85b09587f2cbb58d7e6ef79a6c318651b819715e
3
+ size 1768747
SoccerTwos/SoccerTwos-100000009.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:40015d85aab6d783bbdee876f63dd75bbd5d0ada3b8c28c2dba9f670b30f90ce
3
+ size 28430606
SoccerTwos/SoccerTwos-110522.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bbdd4fd83074319879be69ba81d9b7784999d83aea5ecd87604a62504849f640
3
+ size 1768747
SoccerTwos/SoccerTwos-110522.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:62397029ae23bbfc8a488579406b43f113a96ab28e1a1c55880b67893f81b676
3
+ size 28430234
SoccerTwos/SoccerTwos-98499983.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:08f2759f134a3767adeb63a4139a15c5fd4d60a9ff12481d003776812918707a
3
+ size 1768747
SoccerTwos/SoccerTwos-98499983.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b267239efd99d37369ec8f674b2b4d21495958c1dab05fe1f9c8e4c2e001de66
3
+ size 28430482
SoccerTwos/SoccerTwos-98999986.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6c10a1e904d7e988582a7f6341699cec5ed12ea19f6f3fce766527d5e13a4fc3
3
+ size 1768747
SoccerTwos/SoccerTwos-98999986.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d85182f9f6737f81d05d8c5a8e7b128faa52a0265c3dd2b22384e01922f5d386
3
+ size 28430482
SoccerTwos/SoccerTwos-99499947.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e420473dbabea2c2d72df3e0c27a45e4fc3655d78dae4f766f1bf553a52e981b
3
+ size 1768747
SoccerTwos/SoccerTwos-99499947.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:105e08a149be8b5cec1cc5365e1451686cfec7386235445d9c354e37ea3d02ff
3
+ size 28430482
SoccerTwos/SoccerTwos-99999997.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:872aa75fa12b10601f59935f85b09587f2cbb58d7e6ef79a6c318651b819715e
3
+ size 1768747
SoccerTwos/SoccerTwos-99999997.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ffd63d4e5751ba7d5ff80c11ef627fbec8ab1054446755a61eb563fcb10d1dc3
3
+ size 28430482
SoccerTwos/checkpoint.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b40447e2185ba7a78ce5590d561b65ecac282548a44b61d9fcdd52f3246612ee
3
+ size 28429366
SoccerTwos/events.out.tfevents.1738646548.tesla03.5092.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e48a4d80dce6818007f6733f93a6c05825fbdfdc05183df610214b2792214d59
3
+ size 1242
SoccerTwos/events.out.tfevents.1738646627.tesla03.5457.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:22c1fd5159a5bc6085b0d59bccd006cab336096b98b1947590c8f4d23c9ff20c
3
+ size 71432
SoccerTwos/events.out.tfevents.1738646947.tesla03.5870.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d643644d4bf0d49bafcf28ce668feabee33eab8e15c20067aba802ff70ba12d3
3
+ size 1242
SoccerTwos/events.out.tfevents.1738647027.tesla03.6546.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0021fdf072d0979906f12857978acdb95373fb1800432e0691377faa2c65535b
3
+ size 1242
SoccerTwos/events.out.tfevents.1738647259.tesla03.6944.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2a42c2b3b0b3dddb1292dab06a591ed125dc3aaf3cc94d18f6cae46d02e36ac8
3
+ size 1242
SoccerTwos/events.out.tfevents.1738647345.tesla03.7360.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a7014dc2e474bfc9de7b01730f3d6065653c61e2e1b61a81ebff45bea48a0d8b
3
+ size 101435974
config.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"default_settings": null, "behaviors": {"SoccerTwos": {"trainer_type": "poca", "hyperparameters": {"batch_size": 2048, "buffer_size": 20480, "learning_rate": 0.0001, "beta": 0.005, "epsilon": 0.2, "lambd": 0.95, "num_epoch": 3, "learning_rate_schedule": "constant", "beta_schedule": "constant", "epsilon_schedule": "constant"}, "checkpoint_interval": 500000, "network_settings": {"normalize": false, "hidden_units": 512, "num_layers": 2, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}, "reward_signals": {"extrinsic": {"gamma": 0.99, "strength": 1.0, "network_settings": {"normalize": false, "hidden_units": 128, "num_layers": 2, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}}}, "init_path": null, "keep_checkpoints": 5, "even_checkpoints": false, "max_steps": 100000000, "time_horizon": 1000, "summary_freq": 10000, "threaded": false, "self_play": {"save_steps": 50000, "team_change": 200000, "swap_steps": 2000, "window": 10, "play_against_latest_model_ratio": 0.5, "initial_elo": 1200.0}, "behavioral_cloning": null}}, "env_settings": {"env_path": "./training-envs-executables/SoccerTwos_linux/SoccerTwos.x86_64", "env_args": null, "base_port": 5005, "num_envs": 1, "num_areas": 1, "timeout_wait": 60, "seed": -1, "max_lifetime_restarts": 10, "restarts_rate_limit_n": 1, "restarts_rate_limit_period_s": 60}, "engine_settings": {"width": 84, "height": 84, "quality_level": 5, "time_scale": 20, "target_frame_rate": -1, "capture_frame_rate": 60, "no_graphics": true, "no_graphics_monitor": false}, "environment_parameters": null, "checkpoint_settings": {"run_id": "SoccerTwos", "initialize_from": null, "load_model": false, "resume": true, "force": false, "train_model": false, "inference": false, "results_dir": "results"}, "torch_settings": {"device": null}, "debug": false}
configuration.yaml ADDED
@@ -0,0 +1,84 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ default_settings: null
2
+ behaviors:
3
+ SoccerTwos:
4
+ trainer_type: poca
5
+ hyperparameters:
6
+ batch_size: 2048
7
+ buffer_size: 20480
8
+ learning_rate: 0.0001
9
+ beta: 0.005
10
+ epsilon: 0.2
11
+ lambd: 0.95
12
+ num_epoch: 3
13
+ learning_rate_schedule: constant
14
+ beta_schedule: constant
15
+ epsilon_schedule: constant
16
+ checkpoint_interval: 500000
17
+ network_settings:
18
+ normalize: false
19
+ hidden_units: 512
20
+ num_layers: 2
21
+ vis_encode_type: simple
22
+ memory: null
23
+ goal_conditioning_type: hyper
24
+ deterministic: false
25
+ reward_signals:
26
+ extrinsic:
27
+ gamma: 0.99
28
+ strength: 1.0
29
+ network_settings:
30
+ normalize: false
31
+ hidden_units: 128
32
+ num_layers: 2
33
+ vis_encode_type: simple
34
+ memory: null
35
+ goal_conditioning_type: hyper
36
+ deterministic: false
37
+ init_path: null
38
+ keep_checkpoints: 5
39
+ even_checkpoints: false
40
+ max_steps: 100000000
41
+ time_horizon: 1000
42
+ summary_freq: 10000
43
+ threaded: false
44
+ self_play:
45
+ save_steps: 50000
46
+ team_change: 200000
47
+ swap_steps: 2000
48
+ window: 10
49
+ play_against_latest_model_ratio: 0.5
50
+ initial_elo: 1200.0
51
+ behavioral_cloning: null
52
+ env_settings:
53
+ env_path: ./training-envs-executables/SoccerTwos_linux/SoccerTwos.x86_64
54
+ env_args: null
55
+ base_port: 5005
56
+ num_envs: 1
57
+ num_areas: 1
58
+ timeout_wait: 60
59
+ seed: -1
60
+ max_lifetime_restarts: 10
61
+ restarts_rate_limit_n: 1
62
+ restarts_rate_limit_period_s: 60
63
+ engine_settings:
64
+ width: 84
65
+ height: 84
66
+ quality_level: 5
67
+ time_scale: 20
68
+ target_frame_rate: -1
69
+ capture_frame_rate: 60
70
+ no_graphics: true
71
+ no_graphics_monitor: false
72
+ environment_parameters: null
73
+ checkpoint_settings:
74
+ run_id: SoccerTwos
75
+ initialize_from: null
76
+ load_model: false
77
+ resume: true
78
+ force: false
79
+ train_model: false
80
+ inference: false
81
+ results_dir: results
82
+ torch_settings:
83
+ device: null
84
+ debug: false
run_logs/Player-0.log ADDED
The diff for this file is too large to render. See raw diff
 
run_logs/timers.json ADDED
@@ -0,0 +1,424 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "name": "root",
3
+ "gauges": {
4
+ "SoccerTwos.Policy.Entropy.mean": {
5
+ "value": 1.9804731607437134,
6
+ "min": 1.7603002786636353,
7
+ "max": 3.2864794731140137,
8
+ "count": 9989
9
+ },
10
+ "SoccerTwos.Policy.Entropy.sum": {
11
+ "value": 35109.828125,
12
+ "min": 13540.841796875,
13
+ "max": 136048.484375,
14
+ "count": 9989
15
+ },
16
+ "SoccerTwos.Environment.EpisodeLength.mean": {
17
+ "value": 68.43076923076923,
18
+ "min": 36.89312977099237,
19
+ "max": 999.0,
20
+ "count": 9989
21
+ },
22
+ "SoccerTwos.Environment.EpisodeLength.sum": {
23
+ "value": 17792.0,
24
+ "min": 12004.0,
25
+ "max": 29012.0,
26
+ "count": 9989
27
+ },
28
+ "SoccerTwos.Self-play.ELO.mean": {
29
+ "value": 1700.359058989727,
30
+ "min": 1186.0417714536345,
31
+ "max": 1770.3868328632068,
32
+ "count": 9933
33
+ },
34
+ "SoccerTwos.Self-play.ELO.sum": {
35
+ "value": 221046.6776686645,
36
+ "min": 2373.325228918181,
37
+ "max": 435352.2459840618,
38
+ "count": 9933
39
+ },
40
+ "SoccerTwos.Step.mean": {
41
+ "value": 99999997.0,
42
+ "min": 119303.0,
43
+ "max": 99999997.0,
44
+ "count": 9989
45
+ },
46
+ "SoccerTwos.Step.sum": {
47
+ "value": 99999997.0,
48
+ "min": 119303.0,
49
+ "max": 99999997.0,
50
+ "count": 9989
51
+ },
52
+ "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": {
53
+ "value": -0.04744688421487808,
54
+ "min": -0.13622507452964783,
55
+ "max": 0.13801249861717224,
56
+ "count": 9989
57
+ },
58
+ "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": {
59
+ "value": -6.215541839599609,
60
+ "min": -24.111839294433594,
61
+ "max": 18.579679489135742,
62
+ "count": 9989
63
+ },
64
+ "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": {
65
+ "value": -0.045730676501989365,
66
+ "min": -0.13729985058307648,
67
+ "max": 0.13171157240867615,
68
+ "count": 9989
69
+ },
70
+ "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": {
71
+ "value": -5.990718841552734,
72
+ "min": -24.302074432373047,
73
+ "max": 18.486358642578125,
74
+ "count": 9989
75
+ },
76
+ "SoccerTwos.Environment.CumulativeReward.mean": {
77
+ "value": 0.0,
78
+ "min": 0.0,
79
+ "max": 0.0,
80
+ "count": 9989
81
+ },
82
+ "SoccerTwos.Environment.CumulativeReward.sum": {
83
+ "value": 0.0,
84
+ "min": 0.0,
85
+ "max": 0.0,
86
+ "count": 9989
87
+ },
88
+ "SoccerTwos.Policy.ExtrinsicReward.mean": {
89
+ "value": 0.1111664121387569,
90
+ "min": -0.7142857142857143,
91
+ "max": 0.4013739124588344,
92
+ "count": 9989
93
+ },
94
+ "SoccerTwos.Policy.ExtrinsicReward.sum": {
95
+ "value": 14.562799990177155,
96
+ "min": -78.1152001619339,
97
+ "max": 56.39639961719513,
98
+ "count": 9989
99
+ },
100
+ "SoccerTwos.Environment.GroupCumulativeReward.mean": {
101
+ "value": 0.1111664121387569,
102
+ "min": -0.7142857142857143,
103
+ "max": 0.4013739124588344,
104
+ "count": 9989
105
+ },
106
+ "SoccerTwos.Environment.GroupCumulativeReward.sum": {
107
+ "value": 14.562799990177155,
108
+ "min": -78.1152001619339,
109
+ "max": 56.39639961719513,
110
+ "count": 9989
111
+ },
112
+ "SoccerTwos.IsTraining.mean": {
113
+ "value": 1.0,
114
+ "min": 1.0,
115
+ "max": 1.0,
116
+ "count": 9989
117
+ },
118
+ "SoccerTwos.IsTraining.sum": {
119
+ "value": 1.0,
120
+ "min": 1.0,
121
+ "max": 1.0,
122
+ "count": 9989
123
+ },
124
+ "SoccerTwos.Losses.PolicyLoss.mean": {
125
+ "value": 0.015794843686550545,
126
+ "min": 0.008467505658700247,
127
+ "max": 0.026008055793742338,
128
+ "count": 4841
129
+ },
130
+ "SoccerTwos.Losses.PolicyLoss.sum": {
131
+ "value": 0.015794843686550545,
132
+ "min": 0.008467505658700247,
133
+ "max": 0.026008055793742338,
134
+ "count": 4841
135
+ },
136
+ "SoccerTwos.Losses.ValueLoss.mean": {
137
+ "value": 0.09537502999107043,
138
+ "min": 3.29065480097294e-06,
139
+ "max": 0.12732511560122173,
140
+ "count": 4841
141
+ },
142
+ "SoccerTwos.Losses.ValueLoss.sum": {
143
+ "value": 0.09537502999107043,
144
+ "min": 3.29065480097294e-06,
145
+ "max": 0.12732511560122173,
146
+ "count": 4841
147
+ },
148
+ "SoccerTwos.Losses.BaselineLoss.mean": {
149
+ "value": 0.09579627265532811,
150
+ "min": 3.1763070865054034e-06,
151
+ "max": 0.12857997516791025,
152
+ "count": 4841
153
+ },
154
+ "SoccerTwos.Losses.BaselineLoss.sum": {
155
+ "value": 0.09579627265532811,
156
+ "min": 3.1763070865054034e-06,
157
+ "max": 0.12857997516791025,
158
+ "count": 4841
159
+ },
160
+ "SoccerTwos.Policy.LearningRate.mean": {
161
+ "value": 9.999999999999998e-05,
162
+ "min": 9.999999999999998e-05,
163
+ "max": 0.0001,
164
+ "count": 4841
165
+ },
166
+ "SoccerTwos.Policy.LearningRate.sum": {
167
+ "value": 9.999999999999998e-05,
168
+ "min": 9.999999999999998e-05,
169
+ "max": 0.0001,
170
+ "count": 4841
171
+ },
172
+ "SoccerTwos.Policy.Epsilon.mean": {
173
+ "value": 0.20000000000000007,
174
+ "min": 0.2,
175
+ "max": 0.20000000000000007,
176
+ "count": 4841
177
+ },
178
+ "SoccerTwos.Policy.Epsilon.sum": {
179
+ "value": 0.20000000000000007,
180
+ "min": 0.2,
181
+ "max": 0.20000000000000007,
182
+ "count": 4841
183
+ },
184
+ "SoccerTwos.Policy.Beta.mean": {
185
+ "value": 0.005000000000000001,
186
+ "min": 0.005,
187
+ "max": 0.005000000000000001,
188
+ "count": 4841
189
+ },
190
+ "SoccerTwos.Policy.Beta.sum": {
191
+ "value": 0.005000000000000001,
192
+ "min": 0.005,
193
+ "max": 0.005000000000000001,
194
+ "count": 4841
195
+ }
196
+ },
197
+ "metadata": {
198
+ "timer_format_version": "0.1.0",
199
+ "start_time_seconds": "1738647344",
200
+ "python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]",
201
+ "command_line_arguments": "/home/zdyin/cjq/anaconda3/envs/rl_sfh/bin/mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos_linux/SoccerTwos.x86_64 --run-id=SoccerTwos --no-graphics --resume",
202
+ "mlagents_version": "1.2.0.dev0",
203
+ "mlagents_envs_version": "1.2.0.dev0",
204
+ "communication_protocol_version": "1.5.0",
205
+ "pytorch_version": "2.6.0+cu124",
206
+ "numpy_version": "1.23.5",
207
+ "end_time_seconds": "1738946699"
208
+ },
209
+ "total": 299354.16240669927,
210
+ "count": 1,
211
+ "self": 0.371550056617707,
212
+ "children": {
213
+ "run_training.setup": {
214
+ "total": 0.019736651796847582,
215
+ "count": 1,
216
+ "self": 0.019736651796847582
217
+ },
218
+ "TrainerController.start_learning": {
219
+ "total": 299353.77111999085,
220
+ "count": 1,
221
+ "self": 180.25203748140484,
222
+ "children": {
223
+ "TrainerController._reset_env": {
224
+ "total": 14.40547392424196,
225
+ "count": 500,
226
+ "self": 14.40547392424196
227
+ },
228
+ "TrainerController.advance": {
229
+ "total": 299158.9352256125,
230
+ "count": 6911125,
231
+ "self": 173.966519233305,
232
+ "children": {
233
+ "env_step": {
234
+ "total": 138621.87230544724,
235
+ "count": 6911125,
236
+ "self": 100595.90839038789,
237
+ "children": {
238
+ "SubprocessEnvManager._take_step": {
239
+ "total": 37926.35033567948,
240
+ "count": 6911125,
241
+ "self": 1084.5613465253264,
242
+ "children": {
243
+ "TorchPolicy.evaluate": {
244
+ "total": 36841.788989154156,
245
+ "count": 12553008,
246
+ "self": 36841.788989154156
247
+ }
248
+ }
249
+ },
250
+ "workers": {
251
+ "total": 99.61357937986031,
252
+ "count": 6911125,
253
+ "self": 0.0,
254
+ "children": {
255
+ "worker_root": {
256
+ "total": 299095.1639590524,
257
+ "count": 6911125,
258
+ "is_parallel": true,
259
+ "self": 217885.10016467609,
260
+ "children": {
261
+ "run_training.setup": {
262
+ "total": 0.0,
263
+ "count": 0,
264
+ "is_parallel": true,
265
+ "self": 0.0,
266
+ "children": {
267
+ "steps_from_proto": {
268
+ "total": 0.003039037808775902,
269
+ "count": 2,
270
+ "is_parallel": true,
271
+ "self": 0.000745533499866724,
272
+ "children": {
273
+ "_process_rank_one_or_two_observation": {
274
+ "total": 0.0022935043089091778,
275
+ "count": 8,
276
+ "is_parallel": true,
277
+ "self": 0.0022935043089091778
278
+ }
279
+ }
280
+ },
281
+ "UnityEnvironment.step": {
282
+ "total": 0.029759398195892572,
283
+ "count": 1,
284
+ "is_parallel": true,
285
+ "self": 0.0007145479321479797,
286
+ "children": {
287
+ "UnityEnvironment._generate_step_input": {
288
+ "total": 0.0005333088338375092,
289
+ "count": 1,
290
+ "is_parallel": true,
291
+ "self": 0.0005333088338375092
292
+ },
293
+ "communicator.exchange": {
294
+ "total": 0.026217684149742126,
295
+ "count": 1,
296
+ "is_parallel": true,
297
+ "self": 0.026217684149742126
298
+ },
299
+ "steps_from_proto": {
300
+ "total": 0.002293857280164957,
301
+ "count": 2,
302
+ "is_parallel": true,
303
+ "self": 0.0004619201645255089,
304
+ "children": {
305
+ "_process_rank_one_or_two_observation": {
306
+ "total": 0.0018319371156394482,
307
+ "count": 8,
308
+ "is_parallel": true,
309
+ "self": 0.0018319371156394482
310
+ }
311
+ }
312
+ }
313
+ }
314
+ }
315
+ }
316
+ },
317
+ "UnityEnvironment.step": {
318
+ "total": 81208.89464817755,
319
+ "count": 6911124,
320
+ "is_parallel": true,
321
+ "self": 4548.448424513917,
322
+ "children": {
323
+ "UnityEnvironment._generate_step_input": {
324
+ "total": 3032.6035381308757,
325
+ "count": 6911124,
326
+ "is_parallel": true,
327
+ "self": 3032.6035381308757
328
+ },
329
+ "communicator.exchange": {
330
+ "total": 59378.30022231117,
331
+ "count": 6911124,
332
+ "is_parallel": true,
333
+ "self": 59378.30022231117
334
+ },
335
+ "steps_from_proto": {
336
+ "total": 14249.542463221587,
337
+ "count": 13822248,
338
+ "is_parallel": true,
339
+ "self": 2663.3379590958357,
340
+ "children": {
341
+ "_process_rank_one_or_two_observation": {
342
+ "total": 11586.204504125752,
343
+ "count": 55288992,
344
+ "is_parallel": true,
345
+ "self": 11586.204504125752
346
+ }
347
+ }
348
+ }
349
+ }
350
+ },
351
+ "steps_from_proto": {
352
+ "total": 1.1691461987793446,
353
+ "count": 998,
354
+ "is_parallel": true,
355
+ "self": 0.21755128493532538,
356
+ "children": {
357
+ "_process_rank_one_or_two_observation": {
358
+ "total": 0.9515949138440192,
359
+ "count": 3992,
360
+ "is_parallel": true,
361
+ "self": 0.9515949138440192
362
+ }
363
+ }
364
+ }
365
+ }
366
+ }
367
+ }
368
+ }
369
+ }
370
+ },
371
+ "trainer_advance": {
372
+ "total": 160363.09640093194,
373
+ "count": 6911125,
374
+ "self": 1271.21095593879,
375
+ "children": {
376
+ "process_trajectory": {
377
+ "total": 36535.69475653628,
378
+ "count": 6911125,
379
+ "self": 36506.54455248546,
380
+ "children": {
381
+ "RLTrainer._checkpoint": {
382
+ "total": 29.15020405082032,
383
+ "count": 200,
384
+ "self": 29.15020405082032
385
+ }
386
+ }
387
+ },
388
+ "_update_policy": {
389
+ "total": 122556.19068845687,
390
+ "count": 4841,
391
+ "self": 14243.348395606037,
392
+ "children": {
393
+ "TorchPOCAOptimizer.update": {
394
+ "total": 108312.84229285084,
395
+ "count": 145233,
396
+ "self": 108312.84229285084
397
+ }
398
+ }
399
+ }
400
+ }
401
+ }
402
+ }
403
+ },
404
+ "trainer_threads": {
405
+ "total": 1.1580996215343475e-06,
406
+ "count": 1,
407
+ "self": 1.1580996215343475e-06
408
+ },
409
+ "TrainerController._save_models": {
410
+ "total": 0.1783818146213889,
411
+ "count": 1,
412
+ "self": 0.0019024787470698357,
413
+ "children": {
414
+ "RLTrainer._checkpoint": {
415
+ "total": 0.17647933587431908,
416
+ "count": 1,
417
+ "self": 0.17647933587431908
418
+ }
419
+ }
420
+ }
421
+ }
422
+ }
423
+ }
424
+ }
run_logs/training_status.json ADDED
@@ -0,0 +1,66 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "stats_format_version": "0.3.0",
4
+ "mlagents_version": "1.2.0.dev0",
5
+ "torch_version": "2.6.0+cu124"
6
+ },
7
+ "SoccerTwos": {
8
+ "elo": 1702.5375256630205,
9
+ "checkpoints": [
10
+ {
11
+ "steps": 98499983,
12
+ "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-98499983.onnx",
13
+ "reward": 0.0,
14
+ "creation_time": 1738942270.136697,
15
+ "auxillary_file_paths": [
16
+ "results/SoccerTwos/SoccerTwos/SoccerTwos-98499983.pt"
17
+ ]
18
+ },
19
+ {
20
+ "steps": 98999986,
21
+ "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-98999986.onnx",
22
+ "reward": 0.0,
23
+ "creation_time": 1738943745.1462321,
24
+ "auxillary_file_paths": [
25
+ "results/SoccerTwos/SoccerTwos/SoccerTwos-98999986.pt"
26
+ ]
27
+ },
28
+ {
29
+ "steps": 99499947,
30
+ "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-99499947.onnx",
31
+ "reward": 0.0,
32
+ "creation_time": 1738945214.5466986,
33
+ "auxillary_file_paths": [
34
+ "results/SoccerTwos/SoccerTwos/SoccerTwos-99499947.pt"
35
+ ]
36
+ },
37
+ {
38
+ "steps": 99999997,
39
+ "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-99999997.onnx",
40
+ "reward": 0.0,
41
+ "creation_time": 1738946698.5254576,
42
+ "auxillary_file_paths": [
43
+ "results/SoccerTwos/SoccerTwos/SoccerTwos-99999997.pt"
44
+ ]
45
+ },
46
+ {
47
+ "steps": 100000009,
48
+ "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-100000009.onnx",
49
+ "reward": 0.0,
50
+ "creation_time": 1738946698.7160673,
51
+ "auxillary_file_paths": [
52
+ "results/SoccerTwos/SoccerTwos/SoccerTwos-100000009.pt"
53
+ ]
54
+ }
55
+ ],
56
+ "final_checkpoint": {
57
+ "steps": 100000009,
58
+ "file_path": "results/SoccerTwos/SoccerTwos.onnx",
59
+ "reward": 0.0,
60
+ "creation_time": 1738946698.7160673,
61
+ "auxillary_file_paths": [
62
+ "results/SoccerTwos/SoccerTwos/SoccerTwos-100000009.pt"
63
+ ]
64
+ }
65
+ }
66
+ }