Hugging Face's logo

milotix
/
dqn-SpaceInvadersNoFrameskip-v4

Reinforcement Learning
stable-baselines3
SpaceInvadersNoFrameskip-v4
deep-reinforcement-learning
Eval Results
Model card Files Community
milotix commited on
Commit
5a6976b
•
1 Parent(s): ad60d0e

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: 163.50 +/- 95.63
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']),
@@ -70,7 +70,7 @@ OrderedDict([('batch_size', 32),
70
  ('exploration_fraction', 0.1),
71
  ('frame_stack', 4),
72
  ('gradient_steps', 1),
73
- ('learning_rate', 0.0001),
74
  ('learning_starts', 100000),
75
  ('n_timesteps', 1000000.0),
76
  ('optimize_memory_usage', False),
 
16
  type: SpaceInvadersNoFrameskip-v4
17
  metrics:
18
  - type: mean_reward
19
+ value: 494.50 +/- 177.94
20
  name: mean_reward
21
  verified: false
22
  ---
 
62
 
63
  ## Hyperparameters
64
  ```python
65
+ OrderedDict([('batch_size', 64),
66
  ('buffer_size', 100000),
67
  ('env_wrapper',
68
  ['stable_baselines3.common.atari_wrappers.AtariWrapper']),
 
70
  ('exploration_fraction', 0.1),
71
  ('frame_stack', 4),
72
  ('gradient_steps', 1),
73
+ ('learning_rate', 4e-05),
74
  ('learning_starts', 100000),
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
- - 3502529879
58
  - - storage
59
  - null
60
  - - study_name
 
54
  - - save_replay_buffer
55
  - false
56
  - - seed
57
+ - 735688572
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
@@ -14,7 +14,7 @@
14
  - - gradient_steps
15
  - 1
16
  - - learning_rate
17
- - 0.0001
18
  - - learning_starts
19
  - 100000
20
  - - n_timesteps
 
1
  !!python/object/apply:collections.OrderedDict
2
  - - - batch_size
3
+ - 64
4
  - - buffer_size
5
  - 100000
6
  - - env_wrapper
 
14
  - - gradient_steps
15
  - 1
16
  - - learning_rate
17
+ - 4.0e-05
18
  - - learning_starts
19
  - 100000
20
  - - n_timesteps
dqn-SpaceInvadersNoFrameskip-v4.zip CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c50a3d7bb9a7c2a8af4a9c31b888fe19ccb541b42ef17335e3dcbd7161dbe239
3
  size 27220208
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:163d3957941888ccaddb230fcadededba0a500ec27062aa52a4b79685175b927
3
  size 27220208
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 sha256:34d18bab4113b54176b22be31f1edd30fa1b1ba1579db84d90fc53309c97e8c2
3
  size 13506236
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5c0452453dfe848852a3dfe9ae6c926df35bf233a4c8be53d2b8903ebdb00f87
3
  size 13506236
dqn-SpaceInvadersNoFrameskip-v4/policy.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:517f055f955cd414f2c9e487167bd2dc293e61de2f9b3c343a53372f7f19f2da
3
  size 13505370
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:03af4686493c2beb94f9fcea923b76f775098a466a85753a7f5c0a57cfe4775e
3
  size 13505370
replay.mp4 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e719567fd8d6c7a549a17130871ad6303a2a56d46167917d7bebc2344daee02d
3
- size 285091
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8deccf7f7454f9bb78c29679c4578f7cd4d5361e6624895ed94cb5f834c78410
3
+ size 216095
results.json CHANGED
@@ -1 +1 @@
1
- {"mean_reward": 163.5, "std_reward": 95.63080047767038, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2024-03-24T18:54:44.953815"}
 
1
+ {"mean_reward": 494.5, "std_reward": 177.93889400577942, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2024-03-25T14:55:22.794067"}
train_eval_metrics.zip CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:379a0b5c038ee94a70b82edac946154404532b8b4f8cfff52869d55c25e8892d
3
- size 36552
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5004aa534b570622c9eae862ab7a97d973a52e233915c84e03a0ed78104dafdd
3
+ size 41434