Hugging Face's logo

brightfarmns
/
atari-games

Reinforcement Learning
stable-baselines3
SpaceInvadersNoFrameskip-v4
deep-reinforcement-learning
Eval Results (legacy)
Model card Files
xet
 Community
brightfarmns commited on
Commit
17ba31e
·
1 Parent(s): 1a321fb

Initial commit

Browse files
Files changed (10) hide show
  1. README.md +5 -5
  2. args.yml +1 -1
  3. config.yml +4 -4
  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: 303.00 +/- 278.35
20
  name: mean_reward
21
  verified: false
22
  ---
@@ -63,19 +63,19 @@ python -m rl_zoo3.push_to_hub --algo dqn --env SpaceInvadersNoFrameskip-v4 -f lo
63
  ## Hyperparameters
64
  ```python
65
  OrderedDict([('batch_size', 32),
66
- ('buffer_size', 5000),
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', 0.0005),
74
- ('learning_starts', 10000),
75
  ('n_timesteps', 1000000.0),
76
  ('optimize_memory_usage', False),
77
  ('policy', 'CnnPolicy'),
78
- ('target_update_interval', 10000),
79
  ('train_freq', 4),
80
  ('normalize', False)])
81
  ```
 
16
  type: SpaceInvadersNoFrameskip-v4
17
  metrics:
18
  - type: mean_reward
19
+ value: 707.00 +/- 346.67
20
  name: mean_reward
21
  verified: false
22
  ---
 
63
  ## Hyperparameters
64
  ```python
65
  OrderedDict([('batch_size', 32),
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', 0.0001),
74
+ ('learning_starts', 100000),
75
  ('n_timesteps', 1000000.0),
76
  ('optimize_memory_usage', False),
77
  ('policy', 'CnnPolicy'),
78
+ ('target_update_interval', 1000),
79
  ('train_freq', 4),
80
  ('normalize', False)])
81
  ```
args.yml CHANGED
@@ -54,7 +54,7 @@
54
  - - save_replay_buffer
55
  - false
56
  - - seed
57
- - 1198808224
58
  - - storage
59
  - null
60
  - - study_name
 
54
  - - save_replay_buffer
55
  - false
56
  - - seed
57
+ - 3185639949
58
  - - storage
59
  - null
60
  - - study_name
config.yml CHANGED
@@ -2,7 +2,7 @@
2
  - - - batch_size
3
  - 32
4
  - - buffer_size
5
- - 5000
6
  - - env_wrapper
7
  - - stable_baselines3.common.atari_wrappers.AtariWrapper
8
  - - exploration_final_eps
@@ -14,9 +14,9 @@
14
  - - gradient_steps
15
  - 1
16
  - - learning_rate
17
- - 0.0005
18
  - - learning_starts
19
- - 10000
20
  - - n_timesteps
21
  - 1000000.0
22
  - - optimize_memory_usage
@@ -24,6 +24,6 @@
24
  - - policy
25
  - CnnPolicy
26
  - - target_update_interval
27
- - 10000
28
  - - train_freq
29
  - 4
 
2
  - - - batch_size
3
  - 32
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
+ - 0.0001
18
  - - learning_starts
19
+ - 100000
20
  - - n_timesteps
21
  - 1000000.0
22
  - - optimize_memory_usage
 
24
  - - policy
25
  - CnnPolicy
26
  - - target_update_interval
27
+ - 1000
28
  - - train_freq
29
  - 4
dqn-SpaceInvadersNoFrameskip-v4.zip CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:64277d1679c1a451d27bb5ec2472aca3afdec8696b076ab8610c3f080e48d046
3
  size 27220124
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:215bffb3609a277759859623452006eb386adffadbd53db36def2fca684c4c70
3
  size 27220124
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 sha256:93485059fc5b308e383155723234478fa549251955234e7312e835e6f6d5c7e5
3
  size 13506236
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4322bf47030e0c972f5332725bf932f9a3cdb03685ae913e87a652f4c2c5ca63
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:ae16380b06d71800834d90a640ff044083dc3db1ea8b2c93b364aac3d2dfd794
3
  size 13505370
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5c4f0a1770adf76019d9939342572f8913b5c8ff5dccc24bb92bc16de8eb891d
3
  size 13505370
replay.mp4 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d3b930464ea6d8cd777ce435ab905cdaacc37ad2ec0a04abe1d64c6861c69de6
3
- size 252537
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8ea4f4ba370edb5ab38194ab39bcecdb787e9a117ea960b0f26369c258367b72
3
+ size 214947
results.json CHANGED
@@ -1 +1 @@
1
- {"mean_reward": 303.0, "std_reward": 278.3451095313155, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2023-11-10T15:26:10.789808"}
 
1
+ {"mean_reward": 707.0, "std_reward": 346.6713140714126, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2023-11-13T09:34:46.774079"}
train_eval_metrics.zip CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a8b95ed303d68cca82295666e90bc23277261f93a395919a3d9f0cbd69e9ba0d
3
- size 48466
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c041f288a3e1c59ac960926f87875e8731793a94ca6f628e80766a166c02a021
3
+ size 37641