Hugging Face's logo

bianxg
/
dqn-SpaceInvadersNoFrameskip-v4

Reinforcement Learning
stable-baselines3
SpaceInvadersNoFrameskip-v4
deep-reinforcement-learning
Eval Results
Model card Files Community
bianxg commited on
Commit
78afc53
•
1 Parent(s): 332510b

Initial commit

Browse files
Files changed (12) 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/_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 +2 -2
  9. dqn-SpaceInvadersNoFrameskip-v4/system_info.txt +7 -7
  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: 268.50 +/- 78.17
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: 607.50 +/- 159.94
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
- - 2080036875
58
  - - storage
59
  - null
60
  - - study_name
 
54
  - - save_replay_buffer
55
  - false
56
  - - seed
57
+ - 772217993
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 sha256:2f45d7f66270de25c14c96207fb6b9eaf28c446f68e8e8c9cf296d6524f1ac71
3
- size 13715083
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ae4f970e7b9f89cc4bb93af038b2a09aab39feddc1c68b4644f776b5e3281a5a
3
+ size 27219869
dqn-SpaceInvadersNoFrameskip-v4/_stable_baselines3_version CHANGED
@@ -1 +1 @@
1
- 2.3.0a2
 
1
+ 2.3.0a1
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 sha256:48c05e81aff7ecd0f369bd5b5e62a085fc8a28341c20fee2103d5e118d4de20f
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:d31884c890af46a374a070c67f9bb237902a7d5ac261e18b540fecc514ca96f6
3
- size 13505370
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2dddb8a74a8abb750402787a8c8bf449f666ca3ad2927f7ec52874bbe12dc7ac
3
+ size 13505178
dqn-SpaceInvadersNoFrameskip-v4/system_info.txt CHANGED
@@ -1,9 +1,9 @@
1
- - OS: Linux-6.1.58+-x86_64-with-glibc2.35 # 1 SMP PREEMPT_DYNAMIC Sat Nov 18 15:31:17 UTC 2023
2
- - Python: 3.10.12
3
- - Stable-Baselines3: 2.3.0a2
4
- - PyTorch: 2.1.0+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-5.15.0-91-generic-x86_64-with-glibc2.31 # 101~20.04.1-Ubuntu SMP Thu Nov 16 14:22:28 UTC 2023
2
+ - Python: 3.11.7
3
+ - Stable-Baselines3: 2.3.0a1
4
+ - PyTorch: 2.1.2
5
+ - GPU Enabled: False
6
+ - Numpy: 1.26.3
7
+ - Cloudpickle: 3.0.0
8
  - Gymnasium: 0.29.1
9
  - OpenAI Gym: 0.26.2
replay.mp4 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:38a799ac9657faeb813344ec56ae265d381f35a430091e2c90337e271719a9db
3
- size 278674
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:83f99f99cce50a7aad1f017a95bb6cd510bcce6498bff7a51657ddcf67b2c69b
3
+ size 218764
results.json CHANGED
@@ -1 +1 @@
1
- {"mean_reward": 268.5, "std_reward": 78.16808811785025, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2024-02-20T06:43:49.822978"}
 
1
+ {"mean_reward": 607.5, "std_reward": 159.94139551723313, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2024-02-21T10:21:23.577490"}
train_eval_metrics.zip CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:00e8cfaf810a19aaa84e7723e453da94445abcae07216236c2f64a118f6836f9
3
- size 5641
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1440ff3c2388e953c83dad1948b5bf5e0105608eb2f41c038911b271b9538f94
3
+ size 37510