Hugging Face's logo

krisha-n
/
dqn-SpaceInvadersNoFrameskip-v4

Reinforcement Learning
stable-baselines3
SpaceInvadersNoFrameskip-v4
deep-reinforcement-learning
Eval Results
Model card Files Community
krisha-n commited on
Commit
be5c6d7
•
1 Parent(s): 74535b1

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/pytorch_variables.pth +1 -1
  9. dqn-SpaceInvadersNoFrameskip-v4/system_info.txt +6 -6
  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: 180.00 +/- 116.10
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', 10000),
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: 329.00 +/- 157.97
20
  name: mean_reward
21
  verified: false
22
  ---
 
72
  ('gradient_steps', 1),
73
  ('learning_rate', 0.0001),
74
  ('learning_starts', 10000),
75
+ ('n_timesteps', 10000),
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
- - 548689578
58
  - - storage
59
  - null
60
  - - study_name
 
54
  - - save_replay_buffer
55
  - false
56
  - - seed
57
+ - 1215387516
58
  - - storage
59
  - null
60
  - - study_name
config.yml CHANGED
@@ -18,7 +18,7 @@
18
  - - learning_starts
19
  - 10000
20
  - - n_timesteps
21
- - 100000.0
22
  - - optimize_memory_usage
23
  - false
24
  - - policy
 
18
  - - learning_starts
19
  - 10000
20
  - - n_timesteps
21
+ - 10000
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 sha256:7a361de589fdc4efeea84bcc99eb5cb76bc552562a26e3ef8a2e53e5ee74b6ff
3
- size 27220198
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ec379ca83d8c53f1a8a20fe5b48ec5f616890d12a27bbd0fa489c5c9b90e8b17
3
+ size 13711181
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 sha256:7f067b1c756e19227a14270f9ee89379310dfc474afddf0ea51d54125b46ac15
3
- size 13506236
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:51f8df70a2e5d6f1478c577de874f669207ffb7dec3e2499745fe3a9c2ca0ef8
3
+ size 1120
dqn-SpaceInvadersNoFrameskip-v4/policy.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:04a28864385912d5661a4fc58fa336e25060514512e8d7b48573863ba66ec75c
3
- size 13505370
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0eeeba9f26d15d47aa47972593e3c099dffed20cb792cdf2e171bfebd6325e9f
3
+ size 13505178
dqn-SpaceInvadersNoFrameskip-v4/pytorch_variables.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0c35cea3b2e60fb5e7e162d3592df775cd400e575a31c72f359fb9e654ab00c5
3
  size 864
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fb4dde0c1ad63b7740276006a06cc491b21b407ea6c889928c223ec77ddad79f
3
  size 864
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: 2.3.0
4
- - PyTorch: 2.2.1+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: Windows-10-10.0.22000-SP0 10.0.22000
2
+ - Python: 3.10.14
3
  - Stable-Baselines3: 2.3.0
4
+ - PyTorch: 2.2.2+cpu
5
+ - GPU Enabled: False
6
+ - Numpy: 1.26.4
7
+ - Cloudpickle: 3.0.0
8
  - Gymnasium: 0.29.1
9
  - OpenAI Gym: 0.26.2
results.json CHANGED
@@ -1 +1 @@
1
- {"mean_reward": 180.0, "std_reward": 116.10340218959993, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2024-04-12T09:28:46.655894"}
 
1
+ {"mean_reward": 329.0, "std_reward": 157.96835126062436, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2024-04-13T20:25:40.563028"}
train_eval_metrics.zip CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:867f1963c9048df461a961b35fac70f8b5fe92b436617a0912b73dc0588f0038
3
- size 5000
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6361aa220119f694347aaba73569f212ed2bc9151df54b90bc79fe038484e627
3
+ size 580