Hugging Face's logo

mixklim
/
dqn-SpaceInvadersNoFrameskip-v4

Reinforcement Learning
stable-baselines3
SpaceInvadersNoFrameskip-v4
deep-reinforcement-learning
Eval Results
Model card Files Community
mixklim commited on
Commit
a015aab
•
1 Parent(s): 8e4082b

Initial commit

Browse files
Files changed (10) 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 +1 -1
  8. dqn-SpaceInvadersNoFrameskip-v4/system_info.txt +2 -2
  9. results.json +1 -1
  10. 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
  ---
@@ -73,7 +73,7 @@ OrderedDict([('batch_size', 32),
73
  ('gradient_steps', 1),
74
  ('learning_rate', 0.0001),
75
  ('learning_starts', 100000),
76
- ('n_timesteps', 100.0),
77
  ('optimize_memory_usage', False),
78
  ('policy', 'CnnPolicy'),
79
  ('target_update_interval', 1000),
 
16
  type: SpaceInvadersNoFrameskip-v4
17
  metrics:
18
  - type: mean_reward
19
+ value: 641.50 +/- 160.08
20
  name: mean_reward
21
  verified: false
22
  ---
 
73
  ('gradient_steps', 1),
74
  ('learning_rate', 0.0001),
75
  ('learning_starts', 100000),
76
+ ('n_timesteps', 1000000.0),
77
  ('optimize_memory_usage', False),
78
  ('policy', 'CnnPolicy'),
79
  ('target_update_interval', 1000),
args.yml CHANGED
@@ -56,7 +56,7 @@
56
  - - save_replay_buffer
57
  - false
58
  - - seed
59
- - 2565693474
60
  - - storage
61
  - null
62
  - - study_name
 
56
  - - save_replay_buffer
57
  - false
58
  - - seed
59
+ - 3581125543
60
  - - storage
61
  - null
62
  - - study_name
config.yml CHANGED
@@ -18,7 +18,7 @@
18
  - - learning_starts
19
  - 100000
20
  - - n_timesteps
21
- - 100.0
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 sha256:30341f0c88715ab60d1727947c45ce74bdcf95b3bb61312f34ab874e3b403493
3
- size 13711514
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a53e0abc0ab7839eca8f034577e05f21874db11e1d396abf3c3a5765041cf32e
3
+ size 27220646
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:ec0af8c40ec4d4d071fde42a298eb18b1df89023499ea159fa1aefa697c55647
3
+ size 13506172
dqn-SpaceInvadersNoFrameskip-v4/policy.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5a4fa8cf9fdb34ab16449eba52ab192977c4269aed2267b96c053979259ae287
3
  size 13505370
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:48aa8aab2864b828da49a2796c35e36b92be6115b2d4e9c1c7a2614ac2a1893e
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 Thu Jun 27 21:05:47 UTC 2024
2
  - Python: 3.10.12
3
  - Stable-Baselines3: 2.4.0a11
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
 
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: 2.4.0a11
4
+ - PyTorch: 2.5.0+cu121
5
  - GPU Enabled: True
6
  - Numpy: 1.26.4
7
+ - Cloudpickle: 3.1.0
8
  - Gymnasium: 0.29.1
9
  - OpenAI Gym: 0.25.2
results.json CHANGED
@@ -1 +1 @@
1
- {"mean_reward": 5.0, "std_reward": 7.0710678118654755, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2024-11-04T21:13:54.739577"}
 
1
+ {"mean_reward": 641.5, "std_reward": 160.07888680272612, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2024-11-05T16:25:32.846861"}
train_eval_metrics.zip CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8e09234e22fd6477d91745ecf12d2d9e3961ca7fe03fc1d83c597317cfb735d1
3
- size 205
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fe7037770ae0322f33ffd13ecf849db9b02ea18dc8e547c98d1b46150ab7116a
3
+ size 37722