Hugging Face's logo

manuu01
/
dqn-SpaceInvadersNoFrameskip-v4

Reinforcement Learning
stable-baselines3
SpaceInvadersNoFrameskip-v4
deep-reinforcement-learning
Eval Results (legacy)
Model card Files
xet
 Community
manuu01 commited on
Commit
4e1311b
·
1 Parent(s): 0fb3c7e

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 +2 -2
  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: 221.00 +/- 47.11
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', 5000),
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: 679.50 +/- 120.92
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
- - 1473377315
58
  - - storage
59
  - null
60
  - - study_name
 
54
  - - save_replay_buffer
55
  - false
56
  - - seed
57
+ - 540623551
58
  - - storage
59
  - null
60
  - - study_name
config.yml CHANGED
@@ -18,7 +18,7 @@
18
  - - learning_starts
19
  - 100000
20
  - - n_timesteps
21
- - 5000
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:d079ae66e858ca1d5967b06ac110ff831b808ff3ebead35ae803b2b57ce7f7fa
3
- size 13709406
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3605881ba4ec1415e456b4fff51649233cb89d8ab3f8c1428fec2febdaa26d42
3
+ size 27218385
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 sha256:0b69a6cb94f8a9599ea4291f66c0618fbf541f7509cd0bdc82e64322acea359b
3
- size 687
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:278ce61ced21741a57a2a5e1a195a6257b8a84788e391c624715bb1573c21f8d
3
+ size 13505739
dqn-SpaceInvadersNoFrameskip-v4/policy.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:69cca3fcff27dd8016ce392318e5dd75272616b9590384372d08f457a1057777
3
- size 13504745
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7cc449457fec05a98867f73891a4e8c77d75efaf810a12d1dc48679e72140443
3
+ size 13504937
dqn-SpaceInvadersNoFrameskip-v4/system_info.txt CHANGED
@@ -2,7 +2,7 @@
2
  - Python: 3.10.12
3
  - Stable-Baselines3: 2.0.0
4
  - PyTorch: 2.0.1+cu118
5
- - GPU Enabled: False
6
  - Numpy: 1.22.4
7
  - Cloudpickle: 2.2.1
8
  - Gymnasium: 0.28.1
 
2
  - Python: 3.10.12
3
  - Stable-Baselines3: 2.0.0
4
  - PyTorch: 2.0.1+cu118
5
+ - GPU Enabled: True
6
  - Numpy: 1.22.4
7
  - Cloudpickle: 2.2.1
8
  - Gymnasium: 0.28.1
replay.mp4 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5f42ec0cbd4a4fda0091113153f74e5169d9e8510bc1c50e5d0e460a19132f6c
3
- size 252295
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fd71a55eb81fce81421567332228e96cad9e7f10c447971e0ea9affff940c9c0
3
+ size 274649
results.json CHANGED
@@ -1 +1 @@
1
- {"mean_reward": 221.0, "std_reward": 47.10626285325551, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2023-07-17T13:24:28.920244"}
 
1
+ {"mean_reward": 679.5, "std_reward": 120.92249583927715, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2023-07-17T15:44:06.028184"}
train_eval_metrics.zip CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d802d77e547b44cc16e62403c85ba2f19dc6112165052bb32f47027f53d80cde
3
- size 414
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:76972c84ec3333edefd9c358cfa32bb1e8c79b96259bebd22f3e4c3b736f1833
3
+ size 35719