Hugging Face's logo

catastropiyush
/
dqn-SpaceInvadersNoFrameskip-v4

Reinforcement Learning
stable-baselines3
SpaceInvadersNoFrameskip-v4
deep-reinforcement-learning
Eval Results
Model card Files Community
catastropiyush commited on
Commit
fea7ec8
•
1 Parent(s): 6bfa467

Initial commit

Browse files
Files changed (12) hide show
  1. README.md +3 -3
  2. args.yml +3 -1
  3. config.yml +2 -2
  4. dqn-SpaceInvadersNoFrameskip-v4.zip +2 -2
  5. dqn-SpaceInvadersNoFrameskip-v4/_stable_baselines3_version +1 -1
  6. dqn-SpaceInvadersNoFrameskip-v4/data +0 -0
  7. dqn-SpaceInvadersNoFrameskip-v4/policy.optimizer.pth +2 -2
  8. dqn-SpaceInvadersNoFrameskip-v4/policy.pth +1 -1
  9. dqn-SpaceInvadersNoFrameskip-v4/system_info.txt +5 -5
  10. replay.mp4 +2 -2
  11. results.json +1 -1
  12. 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: 667.50 +/- 154.33
20
  name: mean_reward
21
  verified: false
22
  ---
@@ -71,8 +71,8 @@ OrderedDict([('batch_size', 32),
71
  ('frame_stack', 4),
72
  ('gradient_steps', 1),
73
  ('learning_rate', 0.0001),
74
- ('learning_starts', 10000),
75
- ('n_timesteps', 1000000.0),
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: 6.50 +/- 10.74
20
  name: mean_reward
21
  verified: false
22
  ---
 
71
  ('frame_stack', 4),
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),
args.yml CHANGED
@@ -9,6 +9,8 @@
9
  - SpaceInvadersNoFrameskip-v4
10
  - - env_kwargs
11
  - null
 
 
12
  - - eval_episodes
13
  - 5
14
  - - eval_freq
@@ -54,7 +56,7 @@
54
  - - save_replay_buffer
55
  - false
56
  - - seed
57
- - 3293103169
58
  - - storage
59
  - null
60
  - - study_name
 
9
  - SpaceInvadersNoFrameskip-v4
10
  - - env_kwargs
11
  - null
12
+ - - eval_env_kwargs
13
+ - null
14
  - - eval_episodes
15
  - 5
16
  - - eval_freq
 
56
  - - save_replay_buffer
57
  - false
58
  - - seed
59
+ - 4158514662
60
  - - storage
61
  - null
62
  - - study_name
config.yml CHANGED
@@ -16,9 +16,9 @@
16
  - - learning_rate
17
  - 0.0001
18
  - - learning_starts
19
- - 10000
20
  - - n_timesteps
21
- - 1000000.0
22
  - - optimize_memory_usage
23
  - false
24
  - - policy
 
16
  - - learning_rate
17
  - 0.0001
18
  - - learning_starts
19
+ - 100000
20
  - - n_timesteps
21
+ - 100000.0
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 sha256:34ab8872d55ae9fa71078cf4a2aef2a2a762d7ef423303d4fdd4a2df21f9ea82
3
- size 27220787
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bba76b86382a529eb9aec42fe23cc3af5bd1eb4d97705e83f2d4f309e0b7ff1b
3
+ size 13715667
dqn-SpaceInvadersNoFrameskip-v4/_stable_baselines3_version CHANGED
@@ -1 +1 @@
1
- 2.3.2
 
1
+ 2.4.0a7
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 sha256:750b1fba2efe3c403041c9e423dba7ecebbea6d0d55fdd68ad8628bdb5ef4355
3
- size 13506236
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:215ea7d8898faa9284464c7109532cf36390d330fccab8d77eeba20628a32876
3
+ size 1120
dqn-SpaceInvadersNoFrameskip-v4/policy.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e37ceb4913c9768a8f52a95469ada7c1885be33324139a4f3219c0a6f813ad8c
3
  size 13505370
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:93a85bb8e9341c0ef0f78c9463b51bc7b1c66b789330ac79e178e6519f131373
3
  size 13505370
dqn-SpaceInvadersNoFrameskip-v4/system_info.txt CHANGED
@@ -1,9 +1,9 @@
1
- - OS: Linux-6.1.85+-x86_64-with-glibc2.35 # 1 SMP PREEMPT_DYNAMIC Sun Apr 28 14:29:16 UTC 2024
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
9
- - OpenAI Gym: 0.26.2
 
1
+ - OS: Linux-6.1.85+-x86_64-with-glibc2.35 # 1 SMP PREEMPT_DYNAMIC Thu Jun 27 21:05:47 UTC 2024
2
  - Python: 3.10.12
3
+ - Stable-Baselines3: 2.4.0a7
4
+ - PyTorch: 2.4.1+cu121
5
  - GPU Enabled: True
6
+ - Numpy: 1.26.4
7
  - Cloudpickle: 2.2.1
8
  - Gymnasium: 0.29.1
9
+ - OpenAI Gym: 0.25.2
replay.mp4 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5bb1ddc0ef63d8fef51e17a0558f6ddbe58c6a18eee90f4fc43b33495e28895d
3
- size 195139
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c4ee3e243890b20c0adfa28ee5ec0e99992fafc39572a68f60ee9a99d62e36c7
3
+ size 292612
results.json CHANGED
@@ -1 +1 @@
1
- {"mean_reward": 667.5, "std_reward": 154.32514377119497, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2024-06-11T06:37:23.920771"}
 
1
+ {"mean_reward": 6.5, "std_reward": 10.735455276791944, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2024-10-01T08:06:30.046476"}
train_eval_metrics.zip CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:cf685825d35889c13c9608b11045d19c46a495d386dc80e74f70aaf7b6308257
3
- size 35462
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9c4c005827bc3d88c51f53b0cb712d428a5c693ec15ce08dbae749b7afc03252
3
+ size 5759