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
23c1004
•
1 Parent(s): 41bb1c4

Initial commit

Browse files
Files changed (10) hide show
  1. README.md +4 -4
  2. args.yml +1 -1
  3. config.yml +3 -3
  4. dqn-SpaceInvadersNoFrameskip-v4.zip +2 -2
  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: 238.50 +/- 104.62
20
  name: mean_reward
21
  verified: false
22
  ---
@@ -62,7 +62,7 @@ python -m rl_zoo3.push_to_hub --algo dqn --env SpaceInvadersNoFrameskip-v4 -f lo
62
 
63
  ## Hyperparameters
64
  ```python
65
- OrderedDict([('batch_size', 64),
66
  ('buffer_size', 10000),
67
  ('env_wrapper',
68
  ['stable_baselines3.common.atari_wrappers.AtariWrapper']),
@@ -71,8 +71,8 @@ OrderedDict([('batch_size', 64),
71
  ('frame_stack', 4),
72
  ('gradient_steps', 1),
73
  ('learning_rate', 0.001),
74
- ('learning_starts', 100000),
75
- ('n_timesteps', 500000.0),
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: 150.00 +/- 129.83
20
  name: mean_reward
21
  verified: false
22
  ---
 
62
 
63
  ## Hyperparameters
64
  ```python
65
+ OrderedDict([('batch_size', 128),
66
  ('buffer_size', 10000),
67
  ('env_wrapper',
68
  ['stable_baselines3.common.atari_wrappers.AtariWrapper']),
 
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),
77
  ('policy', 'CnnPolicy'),
78
  ('target_update_interval', 1000),
args.yml CHANGED
@@ -54,7 +54,7 @@
54
  - - save_replay_buffer
55
  - false
56
  - - seed
57
- - 59260341
58
  - - storage
59
  - null
60
  - - study_name
 
54
  - - save_replay_buffer
55
  - false
56
  - - seed
57
+ - 1698248090
58
  - - storage
59
  - null
60
  - - study_name
config.yml CHANGED
@@ -1,6 +1,6 @@
1
  !!python/object/apply:collections.OrderedDict
2
  - - - batch_size
3
- - 64
4
  - - buffer_size
5
  - 10000
6
  - - env_wrapper
@@ -16,9 +16,9 @@
16
  - - learning_rate
17
  - 0.001
18
  - - learning_starts
19
- - 100000
20
  - - n_timesteps
21
- - 500000.0
22
  - - optimize_memory_usage
23
  - false
24
  - - policy
 
1
  !!python/object/apply:collections.OrderedDict
2
  - - - batch_size
3
+ - 128
4
  - - buffer_size
5
  - 10000
6
  - - env_wrapper
 
16
  - - learning_rate
17
  - 0.001
18
  - - learning_starts
19
+ - 10000
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:de4a423a6f41746d694bbd32d1cea5e4c3fded6f0381994f430fad0bb070ea53
3
- size 27220133
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e4faee5ac66c161a10b856e9b180e7a0116a2793aaa2176f583be06941749105
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 sha256:8b8f0237870c0c84841c66e9c594dba445789c5e2b5dd5ebf98f9b7d5c4f4a70
3
  size 13506236
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d6a96e9ea60c2562e1904a02ea808027b0317a742eb3211198b9918716da49ec
3
  size 13506236
dqn-SpaceInvadersNoFrameskip-v4/policy.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0c025eb6dcfb544c621b5b1635bbbf8baf2884aa84fbda9f55b815f0f4a9f2be
3
  size 13505370
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0fa1dbb1d69d13fe0a5d39ee6f99f2b905fd36d3f1c7faf6e3973fa582e17f70
3
  size 13505370
replay.mp4 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:565e8f1ecebd5cfcdc011d691b5e4abc26f7eceab62c4655a7f8183776f5d205
3
- size 252705
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1aa96a337b8ee251c0a54d0dee5fb9be258ccadf80568751891d8c36bb79bb64
3
+ size 265578
results.json CHANGED
@@ -1 +1 @@
1
- {"mean_reward": 238.5, "std_reward": 104.6195488424606, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2024-01-17T16:19:07.864862"}
 
1
+ {"mean_reward": 150.0, "std_reward": 129.82680770934792, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2024-01-17T17:46:46.723753"}
train_eval_metrics.zip CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8b6df222825652fc81a623a619a350f4dba3f3c1b042365e4c1b8551c2d361ae
3
- size 24556
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:01ed2d4ba8d7071bd094d480154047b9eedfcffc95812f220aad3f59befb043d
3
+ size 46312