Hugging Face's logo

andrewsamce
/
dqn-SpaceInvadersNoFrameskip-v4

Reinforcement Learning
stable-baselines3
SpaceInvadersNoFrameskip-v4
deep-reinforcement-learning
Eval Results
Model card Files Community
andrewsamce commited on
Commit
7c694e5
·
verified ·
1 Parent(s): 731221d

Initial commit

Browse files
Files changed (9) 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. results.json +1 -1
  9. 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: 224.00 +/- 94.63
20
  name: mean_reward
21
  verified: false
22
  ---
@@ -63,7 +63,7 @@ python -m rl_zoo3.push_to_hub --algo dqn --env SpaceInvadersNoFrameskip-v4 -f lo
63
 
64
  ## Hyperparameters
65
  ```python
66
- OrderedDict([('batch_size', 32),
67
  ('buffer_size', 100000),
68
  ('env_wrapper',
69
  ['stable_baselines3.common.atari_wrappers.AtariWrapper']),
@@ -71,9 +71,9 @@ OrderedDict([('batch_size', 32),
71
  ('exploration_fraction', 0.1),
72
  ('frame_stack', 4),
73
  ('gradient_steps', 1),
74
- ('learning_rate', 0.001),
75
  ('learning_starts', 100000),
76
- ('n_timesteps', 1000000.0),
77
  ('optimize_memory_usage', False),
78
  ('policy', 'CnnPolicy'),
79
  ('target_update_interval', 1000),
 
16
  type: SpaceInvadersNoFrameskip-v4
17
  metrics:
18
  - type: mean_reward
19
+ value: 257.00 +/- 38.81
20
  name: mean_reward
21
  verified: false
22
  ---
 
63
 
64
  ## Hyperparameters
65
  ```python
66
+ OrderedDict([('batch_size', 256),
67
  ('buffer_size', 100000),
68
  ('env_wrapper',
69
  ['stable_baselines3.common.atari_wrappers.AtariWrapper']),
 
71
  ('exploration_fraction', 0.1),
72
  ('frame_stack', 4),
73
  ('gradient_steps', 1),
74
+ ('learning_rate', 0.0005),
75
  ('learning_starts', 100000),
76
+ ('n_timesteps', 60000.0),
77
  ('optimize_memory_usage', False),
78
  ('policy', 'CnnPolicy'),
79
  ('target_update_interval', 1000),
args.yml CHANGED
@@ -56,7 +56,7 @@
56
  - - save_replay_buffer
57
  - false
58
  - - seed
59
- - 2266581330
60
  - - storage
61
  - null
62
  - - study_name
 
56
  - - save_replay_buffer
57
  - false
58
  - - seed
59
+ - 409421683
60
  - - storage
61
  - null
62
  - - 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
@@ -14,11 +14,11 @@
14
  - - gradient_steps
15
  - 1
16
  - - learning_rate
17
- - 0.001
18
  - - learning_starts
19
  - 100000
20
  - - n_timesteps
21
- - 1000000.0
22
  - - optimize_memory_usage
23
  - false
24
  - - policy
 
1
  !!python/object/apply:collections.OrderedDict
2
  - - - batch_size
3
+ - 256
4
  - - buffer_size
5
  - 100000
6
  - - env_wrapper
 
14
  - - gradient_steps
15
  - 1
16
  - - learning_rate
17
+ - 0.0005
18
  - - learning_starts
19
  - 100000
20
  - - n_timesteps
21
+ - 60000.0
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:cdf5d7b1e1dc5fa2c0eab0ccb3a7c67c675ebd5b6e3a61adf734fbbdb7e13ce5
3
- size 13713382
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f53783fd3ac72d26336a7516a70fd884fccf5b69d6ed936a0639d5169a086676
3
+ size 13713363
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 sha256:9ebba6ecb40924ab5e69c1644febc657308bd2e400895c9595ed25c1fe6cbe34
3
  size 1120
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d3505d6b17f7aa3c95e4f69980c732512f2c2b9e362b04fe48bcd0792177bd52
3
  size 1120
dqn-SpaceInvadersNoFrameskip-v4/policy.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:369f34e9b5616d82256fe648b28f2e9a3d89195e1e2b319905d691c3962c0e68
3
  size 13505370
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:177bf14b5037c9c1794085837041c69b3775a2ca4b63e8cdbe575c54219839ce
3
  size 13505370
results.json CHANGED
@@ -1 +1 @@
1
- {"mean_reward": 224.0, "std_reward": 94.62557793746889, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2025-06-24T14:41:19.442445"}
 
1
+ {"mean_reward": 257.0, "std_reward": 38.80721582386451, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2025-06-24T15:11:35.935152"}
train_eval_metrics.zip CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:912741fddba83202308488193342c52695cf0dd7f7cb96cebaf19d2ab59f0a8b
3
- size 3611
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:44ca723500ae1e400d1a766872f6186257fa32e6b3c41a43b4a08969b3e55112
3
+ size 3776