Hugging Face's logo

mashaal24
/
dqn-SpaceInvadersNoFrameskip-v4

Reinforcement Learning
stable-baselines3
SpaceInvadersNoFrameskip-v4
deep-reinforcement-learning
Eval Results
Model card Files Community
mashaal24 commited on
Commit
8aa5b92
•
1 Parent(s): 95c7980

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 +0 -0
  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: 5.00 +/- 7.07
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: 238.50 +/- 79.47
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
@@ -56,7 +56,7 @@
56
  - - save_replay_buffer
57
  - false
58
  - - seed
59
- - 4094898773
60
  - - storage
61
  - null
62
  - - study_name
 
56
  - - save_replay_buffer
57
  - false
58
  - - seed
59
+ - 4047055324
60
  - - storage
61
  - null
62
  - - 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:b0d9a7b1a7ede03dee22293a1eb1b30e3935d83056af30a052f419ffae383bf8
3
- size 13715667
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:37a0c5006e68fe95c1ad1201d6f4b19f243afda66c34637b74a81bfaf574d2da
3
+ size 27220228
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 sha256:215ea7d8898faa9284464c7109532cf36390d330fccab8d77eeba20628a32876
3
- size 1120
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6b8714ebd80940fd7d862f0c7899934316815dc8f3240a69a16b11cb32203074
3
+ size 13505852
dqn-SpaceInvadersNoFrameskip-v4/policy.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e47c8bbeb84b5674dd281caabd263f73357f137c840a520b0f6d8d816f0a5e6c
3
- size 13505370
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2c6c9c4f7f1adf16318e99b1e0d46282dae866774873a4795ae93a889308fcc7
3
+ size 13505178
dqn-SpaceInvadersNoFrameskip-v4/system_info.txt CHANGED
@@ -2,7 +2,7 @@
2
  - Python: 3.10.12
3
  - Stable-Baselines3: 2.4.0a7
4
  - PyTorch: 2.3.1+cu121
5
- - GPU Enabled: True
6
  - Numpy: 1.26.4
7
  - Cloudpickle: 2.2.1
8
  - Gymnasium: 0.29.1
 
2
  - Python: 3.10.12
3
  - Stable-Baselines3: 2.4.0a7
4
  - PyTorch: 2.3.1+cu121
5
+ - GPU Enabled: False
6
  - Numpy: 1.26.4
7
  - Cloudpickle: 2.2.1
8
  - Gymnasium: 0.29.1
replay.mp4 CHANGED
Binary files a/replay.mp4 and b/replay.mp4 differ
 
results.json CHANGED
@@ -1 +1 @@
1
- {"mean_reward": 5.0, "std_reward": 7.0710678118654755, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2024-08-06T18:22:12.396826"}
 
1
+ {"mean_reward": 238.5, "std_reward": 79.46854723725608, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2024-08-08T17:38:23.915883"}
train_eval_metrics.zip CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:37bd4b98c4d999a50d44193d4a17da6acb49d2e1a7809f883e534ac5705b9a54
3
- size 5874
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9f0813b5e8d095597ca56e10004db8d708f116c1e0a67e7f91f8d4c025743ea2
3
+ size 7872