Hugging Face's logo

ValentinGuigon
/
dqn-SpaceInvadersNoFrameskip-v4

Reinforcement Learning
stable-baselines3
SpaceInvadersNoFrameskip-v4
deep-reinforcement-learning
Eval Results
Model card Files Community
ValentinGuigon commited on
Commit
7235a9a
•
1 Parent(s): f6a47ff

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 +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: 189.50 +/- 109.35
20
  name: mean_reward
21
  verified: false
22
  ---
@@ -63,16 +63,16 @@ 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', 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', 500000.0),
76
  ('optimize_memory_usage', False),
77
  ('policy', 'CnnPolicy'),
78
  ('target_update_interval', 1000),
 
16
  type: SpaceInvadersNoFrameskip-v4
17
  metrics:
18
  - type: mean_reward
19
+ value: 29.00 +/- 64.30
20
  name: mean_reward
21
  verified: false
22
  ---
 
63
  ## Hyperparameters
64
  ```python
65
  OrderedDict([('batch_size', 32),
66
+ ('buffer_size', 1000000),
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', 0.01),
74
+ ('learning_starts', 10000),
75
+ ('n_timesteps', 100000.0),
76
  ('optimize_memory_usage', False),
77
  ('policy', 'CnnPolicy'),
78
  ('target_update_interval', 1000),
args.yml CHANGED
@@ -56,7 +56,7 @@
56
  - - save_replay_buffer
57
  - false
58
  - - seed
59
- - 3621513077
60
  - - storage
61
  - null
62
  - - study_name
 
56
  - - save_replay_buffer
57
  - false
58
  - - seed
59
+ - 3875727083
60
  - - storage
61
  - null
62
  - - study_name
config.yml CHANGED
@@ -2,7 +2,7 @@
2
  - - - batch_size
3
  - 32
4
  - - buffer_size
5
- - 100000
6
  - - env_wrapper
7
  - - stable_baselines3.common.atari_wrappers.AtariWrapper
8
  - - exploration_final_eps
@@ -14,11 +14,11 @@
14
  - - gradient_steps
15
  - 1
16
  - - learning_rate
17
- - 0.0001
18
  - - learning_starts
19
- - 100000
20
  - - n_timesteps
21
- - 500000.0
22
  - - optimize_memory_usage
23
  - false
24
  - - policy
 
2
  - - - batch_size
3
  - 32
4
  - - buffer_size
5
+ - 1000000
6
  - - env_wrapper
7
  - - stable_baselines3.common.atari_wrappers.AtariWrapper
8
  - - exploration_final_eps
 
14
  - - gradient_steps
15
  - 1
16
  - - learning_rate
17
+ - 0.01
18
  - - learning_starts
19
+ - 10000
20
  - - n_timesteps
21
+ - 100000.0
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:eac5a8ce3b01e24c69cfa0e82bad143d0f0e79507fcddf10746940f7c91118e9
3
- size 27220725
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:64ac5d6fb452aec5a499256e8eb29b41de48581a0a00162069d5f973773fd644
3
+ size 27220722
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 sha256:901b29c7526894304b7a76bbdce2f5f51a2d067140ed1c31797f2a9ee217491a
3
  size 13506172
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b79d4d52a7733a851b736e4f63b0f2007f8a75d206eb5b3919cdf98902126716
3
  size 13506172
dqn-SpaceInvadersNoFrameskip-v4/policy.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:63ab1f3ce0beedb9160a0d01d1dd8af7854917e806534c4ceec0a27c41cf41c7
3
  size 13505370
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:47759d3bdddbe23dead13d3f560e6fce89246c6f73f5ac292bf2428b99c3daaf
3
  size 13505370
replay.mp4 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7aea8fd873879f697b842abb34bebaa7bacc9cc2bafd80c49bb9c4e217ec0c07
3
- size 250198
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6332f13a1224ba686797bd770b10af974d632c130bd192c46a69bdf79b1811c4
3
+ size 294871
results.json CHANGED
@@ -1 +1 @@
1
- {"mean_reward": 189.5, "std_reward": 109.34921124544063, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2024-09-14T16:46:33.295409"}
 
1
+ {"mean_reward": 29.0, "std_reward": 64.29618962271404, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2024-09-14T17:01:21.733283"}
train_eval_metrics.zip CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:27e0801bbe4acf8da83513c48f92cd518e95d48557d9cb622549d20a76440ab0
3
- size 21860
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6250f705c487a6f738b7d8c0a9378c656c488b4cc28136d0ea5e19ca40be8667
3
+ size 4904