Hugging Face's logo

ValentinGuigon
/
dqn-SpaceInvadersNoFrameskip-v4

Reinforcement Learning
stable-baselines3
SpaceInvadersNoFrameskip-v4
deep-reinforcement-learning
Eval Results
Model card Files Community
ValentinGuigon commited on
Commit
f6a47ff
•
1 Parent(s): fc48afa

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: 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: 189.50 +/- 109.35
20
  name: mean_reward
21
  verified: false
22
  ---
 
72
  ('gradient_steps', 1),
73
  ('learning_rate', 0.0001),
74
  ('learning_starts', 100000),
75
+ ('n_timesteps', 500000.0),
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
- - 3490009210
60
  - - storage
61
  - null
62
  - - study_name
 
56
  - - save_replay_buffer
57
  - false
58
  - - seed
59
+ - 3621513077
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
+ - 500000.0
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 sha256:115de63d5bc9288044708050d30e0d21db7698f01f775100fd9f269cf25a7e27
3
- size 13715476
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eac5a8ce3b01e24c69cfa0e82bad143d0f0e79507fcddf10746940f7c91118e9
3
+ size 27220725
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 sha256:901b29c7526894304b7a76bbdce2f5f51a2d067140ed1c31797f2a9ee217491a
3
+ size 13506172
dqn-SpaceInvadersNoFrameskip-v4/policy.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:bdd13775d52fe9fcfa830dae42e39bfbda175e4667e34ea40611283b0ba35617
3
- size 13505178
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:63ab1f3ce0beedb9160a0d01d1dd8af7854917e806534c4ceec0a27c41cf41c7
3
+ size 13505370
dqn-SpaceInvadersNoFrameskip-v4/system_info.txt CHANGED
@@ -2,7 +2,7 @@
2
  - Python: 3.10.12
3
  - Stable-Baselines3: 2.4.0a7
4
  - PyTorch: 2.4.0+cu121
5
- - GPU Enabled: False
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: 2.4.0+cu121
5
+ - GPU Enabled: True
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": 329.0, "std_reward": 157.96835126062436, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2024-09-12T20:31:09.461769"}
 
1
+ {"mean_reward": 189.5, "std_reward": 109.34921124544063, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2024-09-14T16:46:33.295409"}
train_eval_metrics.zip CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1a104921408034dac35e3f95bea8651732241a427fa318fe3a35fd8eea1bbddc
3
- size 5798
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:27e0801bbe4acf8da83513c48f92cd518e95d48557d9cb622549d20a76440ab0
3
+ size 21860