Hugging Face's logo

IrinaArcadievna
/
dqn-SpaceInvadersNoFrameskip-v4

Reinforcement Learning
stable-baselines3
SpaceInvadersNoFrameskip-v4
deep-reinforcement-learning
Eval Results
Model card Files Community
IrinaArcadievna commited on
Commit
c215699
•
1 Parent(s): 23c1004

Initial commit

Browse files
Files changed (10) hide show
  1. README.md +3 -3
  2. args.yml +1 -1
  3. config.yml +2 -2
  4. dqn-SpaceInvadersNoFrameskip-v4.zip +1 -1
  5. dqn-SpaceInvadersNoFrameskip-v4/data +0 -0
  6. dqn-SpaceInvadersNoFrameskip-v4/policy.optimizer.pth +1 -1
  7. dqn-SpaceInvadersNoFrameskip-v4/policy.pth +1 -1
  8. replay.mp4 +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: 150.00 +/- 129.83
20
  name: mean_reward
21
  verified: false
22
  ---
@@ -63,14 +63,14 @@ python -m rl_zoo3.push_to_hub --algo dqn --env SpaceInvadersNoFrameskip-v4 -f lo
63
  ## Hyperparameters
64
  ```python
65
  OrderedDict([('batch_size', 128),
66
- ('buffer_size', 10000),
67
  ('env_wrapper',
68
  ['stable_baselines3.common.atari_wrappers.AtariWrapper']),
69
  ('exploration_final_eps', 0.01),
70
  ('exploration_fraction', 0.1),
71
  ('frame_stack', 4),
72
  ('gradient_steps', 1),
73
- ('learning_rate', 0.001),
74
  ('learning_starts', 10000),
75
  ('n_timesteps', 1000000.0),
76
  ('optimize_memory_usage', False),
 
16
  type: SpaceInvadersNoFrameskip-v4
17
  metrics:
18
  - type: mean_reward
19
+ value: 409.50 +/- 78.63
20
  name: mean_reward
21
  verified: false
22
  ---
 
63
  ## Hyperparameters
64
  ```python
65
  OrderedDict([('batch_size', 128),
66
+ ('buffer_size', 100000),
67
  ('env_wrapper',
68
  ['stable_baselines3.common.atari_wrappers.AtariWrapper']),
69
  ('exploration_final_eps', 0.01),
70
  ('exploration_fraction', 0.1),
71
  ('frame_stack', 4),
72
  ('gradient_steps', 1),
73
+ ('learning_rate', 0.0003),
74
  ('learning_starts', 10000),
75
  ('n_timesteps', 1000000.0),
76
  ('optimize_memory_usage', False),
args.yml CHANGED
@@ -54,7 +54,7 @@
54
  - - save_replay_buffer
55
  - false
56
  - - seed
57
- - 1698248090
58
  - - storage
59
  - null
60
  - - study_name
 
54
  - - save_replay_buffer
55
  - false
56
  - - seed
57
+ - 2104970303
58
  - - storage
59
  - null
60
  - - study_name
config.yml CHANGED
@@ -2,7 +2,7 @@
2
  - - - batch_size
3
  - 128
4
  - - buffer_size
5
- - 10000
6
  - - env_wrapper
7
  - - stable_baselines3.common.atari_wrappers.AtariWrapper
8
  - - exploration_final_eps
@@ -14,7 +14,7 @@
14
  - - gradient_steps
15
  - 1
16
  - - learning_rate
17
- - 0.001
18
  - - learning_starts
19
  - 10000
20
  - - n_timesteps
 
2
  - - - batch_size
3
  - 128
4
  - - buffer_size
5
+ - 100000
6
  - - env_wrapper
7
  - - stable_baselines3.common.atari_wrappers.AtariWrapper
8
  - - exploration_final_eps
 
14
  - - gradient_steps
15
  - 1
16
  - - learning_rate
17
+ - 0.0003
18
  - - learning_starts
19
  - 10000
20
  - - n_timesteps
dqn-SpaceInvadersNoFrameskip-v4.zip CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e4faee5ac66c161a10b856e9b180e7a0116a2793aaa2176f583be06941749105
3
  size 27220136
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cf40da846257b4c6eb3c3018d0b629e9c5cd7cbdc8c6bcb1c230059f6bf58833
3
  size 27220136
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:d6a96e9ea60c2562e1904a02ea808027b0317a742eb3211198b9918716da49ec
3
  size 13506236
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a209206996306c3c5e9348d7976b14abc67ad638a7c5c1a34c9f83d112f87d4a
3
  size 13506236
dqn-SpaceInvadersNoFrameskip-v4/policy.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0fa1dbb1d69d13fe0a5d39ee6f99f2b905fd36d3f1c7faf6e3973fa582e17f70
3
  size 13505370
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c042ef80f3c45a0737063c452929ee3f497396b0642620f4e0e01da2d455ca42
3
  size 13505370
replay.mp4 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1aa96a337b8ee251c0a54d0dee5fb9be258ccadf80568751891d8c36bb79bb64
3
- size 265578
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0fd7250ae88ce38bcbb7df71b82527f65df58035141495b6a6f61a08d70bde66
3
+ size 246664
results.json CHANGED
@@ -1 +1 @@
1
- {"mean_reward": 150.0, "std_reward": 129.82680770934792, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2024-01-17T17:46:46.723753"}
 
1
+ {"mean_reward": 409.5, "std_reward": 78.62728534039567, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2024-01-17T20:55:32.722046"}
train_eval_metrics.zip CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:01ed2d4ba8d7071bd094d480154047b9eedfcffc95812f220aad3f59befb043d
3
- size 46312
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:10d699bc64a736db16608d9001debc076527f6d480d86aa894ebeaec35fcccef
3
+ size 39335