Hugging Face's logo

JohnRLAccount
/
dqn-SpaceInvadersNoFrameskip-v4

Reinforcement Learning
stable-baselines3
SpaceInvadersNoFrameskip-v4
deep-reinforcement-learning
Eval Results
Model card Files Community
JohnRLAccount commited on
Commit
23bccc5
·
1 Parent(s): 428b623

Initial commit

Browse files
Files changed (11) hide show
  1. README.md +2 -2
  2. args.yml +1 -1
  3. config.yml +1 -1
  4. dqn-SpaceInvadersNoFrameskip-v4.zip +2 -2
  5. dqn-SpaceInvadersNoFrameskip-v4/data +0 -0
  6. dqn-SpaceInvadersNoFrameskip-v4/policy.optimizer.pth +2 -2
  7. dqn-SpaceInvadersNoFrameskip-v4/policy.pth +2 -2
  8. dqn-SpaceInvadersNoFrameskip-v4/system_info.txt +1 -1
  9. replay.mp4 +2 -2
  10. results.json +1 -1
  11. train_eval_metrics.zip +2 -2
README.md CHANGED
@@ -16,7 +16,7 @@ model-index:
16
  type: SpaceInvadersNoFrameskip-v4
17
  metrics:
18
  - type: mean_reward
19
- value: 329.00 +/- 157.97
20
  name: mean_reward
21
  verified: false
22
  ---
@@ -72,7 +72,7 @@ OrderedDict([('batch_size', 32),
72
  ('gradient_steps', 1),
73
  ('learning_rate', 0.0001),
74
  ('learning_starts', 100000),
75
- ('n_timesteps', 100000.0),
76
  ('optimize_memory_usage', False),
77
  ('policy', 'CnnPolicy'),
78
  ('target_update_interval', 1000),
 
16
  type: SpaceInvadersNoFrameskip-v4
17
  metrics:
18
  - type: mean_reward
19
+ value: 500.50 +/- 156.90
20
  name: mean_reward
21
  verified: false
22
  ---
 
72
  ('gradient_steps', 1),
73
  ('learning_rate', 0.0001),
74
  ('learning_starts', 100000),
75
+ ('n_timesteps', 1000000.0),
76
  ('optimize_memory_usage', False),
77
  ('policy', 'CnnPolicy'),
78
  ('target_update_interval', 1000),
args.yml CHANGED
@@ -54,7 +54,7 @@
54
  - - save_replay_buffer
55
  - false
56
  - - seed
57
- - 726637096
58
  - - storage
59
  - null
60
  - - study_name
 
54
  - - save_replay_buffer
55
  - false
56
  - - seed
57
+ - 3094670154
58
  - - storage
59
  - null
60
  - - study_name
config.yml CHANGED
@@ -18,7 +18,7 @@
18
  - - learning_starts
19
  - 100000
20
  - - n_timesteps
21
- - 100000.0
22
  - - optimize_memory_usage
23
  - false
24
  - - policy
 
18
  - - learning_starts
19
  - 100000
20
  - - n_timesteps
21
+ - 1000000.0
22
  - - optimize_memory_usage
23
  - false
24
  - - policy
dqn-SpaceInvadersNoFrameskip-v4.zip CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:722b668b6c5674f0b7a18907d0594e2eae36c7d3f2247892efd98a73cf5af388
3
- size 13715472
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fc6a2b1ca405c45712d69a84f38ce6c19acab00381500cff38066078eb9c1792
3
+ size 27220788
dqn-SpaceInvadersNoFrameskip-v4/data CHANGED
The diff for this file is too large to render. See raw diff
 
dqn-SpaceInvadersNoFrameskip-v4/policy.optimizer.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e3fc84919e676e2bdcaa04814c7dfa2b7625d8d53a818418c6db25771364db93
3
- size 1120
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c332121b6649dd01c3ad1e26a2c9198de44d2801d21b4ff4510d97f08e15050a
3
+ size 13506236
dqn-SpaceInvadersNoFrameskip-v4/policy.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:bc43ba239bb87a0d0e790d18ca9be7148d3c02252c0d158fbd6156efee275555
3
- size 13505178
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:68f57644dac7fbfa2a8593ad1ffcc7e30d66e4827d4fa0b7435f50c0067cf56e
3
+ size 13505370
dqn-SpaceInvadersNoFrameskip-v4/system_info.txt CHANGED
@@ -2,7 +2,7 @@
2
  - Python: 3.10.12
3
  - Stable-Baselines3: 2.3.2
4
  - PyTorch: 2.3.0+cu121
5
- - GPU Enabled: False
6
  - Numpy: 1.25.2
7
  - Cloudpickle: 2.2.1
8
  - Gymnasium: 0.29.1
 
2
  - Python: 3.10.12
3
  - Stable-Baselines3: 2.3.2
4
  - PyTorch: 2.3.0+cu121
5
+ - GPU Enabled: True
6
  - Numpy: 1.25.2
7
  - Cloudpickle: 2.2.1
8
  - Gymnasium: 0.29.1
replay.mp4 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d1220fd2663a829192a2b709c767eb2debf32246e6f8d3b5838a5840975ff8d0
3
- size 242623
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c423b022fb3a6f6e4001f9a1de8c5a45cc1de98067f88c21488f9cce9f79390b
3
+ size 248133
results.json CHANGED
@@ -1 +1 @@
1
- {"mean_reward": 329.0, "std_reward": 157.96835126062436, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2024-06-04T12:56:49.379153"}
 
1
+ {"mean_reward": 500.5, "std_reward": 156.89885276827235, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2024-06-05T08:32:19.049062"}
train_eval_metrics.zip CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7c34fa91e4fe4dc3dea9caa2aff5f89a0897c27bebfa926b5f0bfa1f840a8b9f
3
- size 5869
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:66c6eb6338246f9832fa02c56d4fc8a32ccbca7c8fa39e98783a3ee98e23bda3
3
+ size 36665