Hugging Face's logo

bochen0909
/
dqn-SpaceInvadersNoFrameskip-v4

Reinforcement Learning
stable-baselines3
SpaceInvadersNoFrameskip-v4
deep-reinforcement-learning
Eval Results (legacy)
Model card Files
xet
 Community
bochen0909 commited on
Commit
ff81db7
·
1 Parent(s): fc70548

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 +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: 757.00 +/- 244.71
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', 32),
66
  ('buffer_size', 100000),
67
  ('env_wrapper',
68
  ['stable_baselines3.common.atari_wrappers.AtariWrapper']),
@@ -72,7 +72,7 @@ OrderedDict([('batch_size', 32),
72
  ('gradient_steps', 1),
73
  ('learning_rate', 0.0001),
74
  ('learning_starts', 100000),
75
- ('n_timesteps', 1000000.0),
76
  ('policy', 'CnnPolicy'),
77
  ('target_update_interval', 1000),
78
  ('train_freq', 4),
 
16
  type: SpaceInvadersNoFrameskip-v4
17
  metrics:
18
  - type: mean_reward
19
+ value: 671.50 +/- 158.70
20
  name: mean_reward
21
  verified: false
22
  ---
 
62
 
63
  ## Hyperparameters
64
  ```python
65
+ OrderedDict([('batch_size', 128),
66
  ('buffer_size', 100000),
67
  ('env_wrapper',
68
  ['stable_baselines3.common.atari_wrappers.AtariWrapper']),
 
72
  ('gradient_steps', 1),
73
  ('learning_rate', 0.0001),
74
  ('learning_starts', 100000),
75
+ ('n_timesteps', 10000000.0),
76
  ('policy', 'CnnPolicy'),
77
  ('target_update_interval', 1000),
78
  ('train_freq', 4),
args.yml CHANGED
@@ -54,7 +54,7 @@
54
  - - save_replay_buffer
55
  - false
56
  - - seed
57
- - 3443751140
58
  - - storage
59
  - null
60
  - - study_name
 
54
  - - save_replay_buffer
55
  - false
56
  - - seed
57
+ - 4007995114
58
  - - storage
59
  - null
60
  - - study_name
config.yml CHANGED
@@ -1,6 +1,6 @@
1
  !!python/object/apply:collections.OrderedDict
2
  - - - batch_size
3
- - 32
4
  - - buffer_size
5
  - 100000
6
  - - env_wrapper
@@ -18,7 +18,7 @@
18
  - - learning_starts
19
  - 100000
20
  - - n_timesteps
21
- - 1000000.0
22
  - - policy
23
  - CnnPolicy
24
  - - target_update_interval
 
1
  !!python/object/apply:collections.OrderedDict
2
  - - - batch_size
3
+ - 128
4
  - - buffer_size
5
  - 100000
6
  - - env_wrapper
 
18
  - - learning_starts
19
  - 100000
20
  - - n_timesteps
21
+ - 10000000.0
22
  - - policy
23
  - CnnPolicy
24
  - - target_update_interval
dqn-SpaceInvadersNoFrameskip-v4.zip CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6e2b39825b32bf1e3329cecfccc865b0def8d4fd4c4ae768d68ca448f3c5a7fe
3
- size 27218857
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6836706180ab06be3198e57406e2cb918b1db23cdeefe5c39496f5375677def9
3
+ size 27218863
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:b94b7069d8a87e8f065f676b9404599a76568b343aac9350681d126979ab565e
3
  size 13505739
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c584b4aded81a45f4dc55d280a6421aa36ada81d34a4f8a8e6cec8dafaed4cec
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:ba6702a4ac525af166e2ef85c7b0c005ca76a85ee383cf55ef9c039bb9baeaef
3
  size 13504937
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c1fb3cbdc5ce2d75732aa43cba537b49be94f8bdc2867cd59aebb27b77e45932
3
  size 13504937
replay.mp4 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4a229548aaaee642a69c54a9dad5337cb41a9c9b6a9e3d84bd61768ff1dcfe67
3
- size 189670
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d4ac1339e1685bf0c99ab2ec4a4d13664772d3fdcd4c1f59337a8823fce10722
3
+ size 205110
results.json CHANGED
@@ -1 +1 @@
1
- {"mean_reward": 757.0, "std_reward": 244.70594598415462, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2023-07-19T13:40:37.941684"}
 
1
+ {"mean_reward": 671.5, "std_reward": 158.6986137305553, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2023-07-26T07:19:14.285355"}
train_eval_metrics.zip CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:994bc8ae74a01b4071560546f9ee23cbd905098ee57948a6a006103ab7220467
3
- size 36520
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a040d967c0ff0b0c9672e2a6988ea8514e8bc3d833a257439fd7be87885a3d5e
3
+ size 306877