Hugging Face's logo

pablot
/
SpaceInvaders

Reinforcement Learning
stable-baselines3
SpaceInvadersNoFrameskip-v4
deep-reinforcement-learning
Eval Results
Model card Files Community
pablot commited on
Commit
c68e0d8
·
1 Parent(s): 70aa43e

Initial commit

Browse files
Files changed (9) hide show
  1. README.md +5 -5
  2. args.yml +1 -1
  3. config.yml +4 -4
  4. dqn-SpaceInvadersNoFrameskip-v4.zip +2 -2
  5. dqn-SpaceInvadersNoFrameskip-v4/data +0 -0
  6. dqn-SpaceInvadersNoFrameskip-v4/policy.optimizer.pth +2 -2
  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: 5.00 +/- 7.07
20
  name: mean_reward
21
  verified: false
22
  ---
@@ -63,15 +63,15 @@ 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', 0.9),
71
  ('frame_stack', 4),
72
  ('gradient_steps', 1),
73
- ('learning_rate', 0.001),
74
- ('learning_starts', 100000),
75
  ('n_timesteps', 100000),
76
  ('optimize_memory_usage', False),
77
  ('policy', 'CnnPolicy'),
 
16
  type: SpaceInvadersNoFrameskip-v4
17
  metrics:
18
  - type: mean_reward
19
+ value: 321.50 +/- 104.69
20
  name: mean_reward
21
  verified: false
22
  ---
 
63
  ## Hyperparameters
64
  ```python
65
  OrderedDict([('batch_size', 32),
66
+ ('buffer_size', 10000),
67
  ('env_wrapper',
68
  ['stable_baselines3.common.atari_wrappers.AtariWrapper']),
69
  ('exploration_final_eps', 0.01),
70
+ ('exploration_fraction', 0.8),
71
  ('frame_stack', 4),
72
  ('gradient_steps', 1),
73
+ ('learning_rate', 0.0001),
74
+ ('learning_starts', 1000),
75
  ('n_timesteps', 100000),
76
  ('optimize_memory_usage', False),
77
  ('policy', 'CnnPolicy'),
args.yml CHANGED
@@ -54,7 +54,7 @@
54
  - - save_replay_buffer
55
  - false
56
  - - seed
57
- - 2255630783
58
  - - storage
59
  - null
60
  - - study_name
 
54
  - - save_replay_buffer
55
  - false
56
  - - seed
57
+ - 4160963437
58
  - - storage
59
  - null
60
  - - study_name
config.yml CHANGED
@@ -2,21 +2,21 @@
2
  - - - batch_size
3
  - 32
4
  - - buffer_size
5
- - 5000
6
  - - env_wrapper
7
  - - stable_baselines3.common.atari_wrappers.AtariWrapper
8
  - - exploration_final_eps
9
  - 0.01
10
  - - exploration_fraction
11
- - 0.9
12
  - - frame_stack
13
  - 4
14
  - - gradient_steps
15
  - 1
16
  - - learning_rate
17
- - 0.001
18
  - - learning_starts
19
- - 100000
20
  - - n_timesteps
21
  - 100000
22
  - - optimize_memory_usage
 
2
  - - - batch_size
3
  - 32
4
  - - buffer_size
5
+ - 10000
6
  - - env_wrapper
7
  - - stable_baselines3.common.atari_wrappers.AtariWrapper
8
  - - exploration_final_eps
9
  - 0.01
10
  - - exploration_fraction
11
+ - 0.8
12
  - - frame_stack
13
  - 4
14
  - - gradient_steps
15
  - 1
16
  - - learning_rate
17
+ - 0.0001
18
  - - learning_starts
19
+ - 1000
20
  - - n_timesteps
21
  - 100000
22
  - - optimize_memory_usage
dqn-SpaceInvadersNoFrameskip-v4.zip CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:269e7340a07ef215034034a554a6923ab52e207b6339f322999ed1051cce7baa
3
- size 13716591
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d5dd2633219de7ca9aac76707194d26ee888256f67825891d3bafc5c4053dc3c
3
+ size 27221649
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:ca1a604bf7883ee03752a956afae3b4644b57b6e7a499a2d4991dc2e4e6689d1
3
+ size 13506172
dqn-SpaceInvadersNoFrameskip-v4/policy.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b0c5fe87effaab40ac72bfff5046ad71b90121ffe617ae98738bfbc7643c6295
3
  size 13505370
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d2777390f21b0ba73f71a5ceb52476bbffa70ddc045d6ffcec01ae04b63b5f5b
3
  size 13505370
results.json CHANGED
@@ -1 +1 @@
1
- {"mean_reward": 5.0, "std_reward": 7.0710678118654755, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2025-05-08T00:09:18.298823"}
 
1
+ {"mean_reward": 321.5, "std_reward": 104.69121262073527, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2025-05-08T00:25:41.299369"}
train_eval_metrics.zip CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2fcd380c82080b7fbfda7f783de83b1ac0fcbbc272e8117e845cc2aab363be58
3
- size 5765
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:728cc0a049a49077fc37219daa4abc071083d906a780d9e122522e9835ea8715
3
+ size 5246