Hugging Face's logo

chaouch
/
dqn-SpaceInvadersNoFrameskip-v4

Reinforcement Learning
stable-baselines3
SpaceInvadersNoFrameskip-v4
deep-reinforcement-learning
Eval Results
Model card Files Community
chaouch commited on
Commit
0a2dcbc
•
1 Parent(s): 11cbc0d

Initial commit

Browse files
Files changed (11) 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 +2 -2
  8. dqn-SpaceInvadersNoFrameskip-v4/system_info.txt +1 -1
  9. replay.mp4 +2 -2
  10. results.json +1 -1
  11. 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: 401.50 +/- 239.43
20
  name: mean_reward
21
  verified: false
22
  ---
@@ -62,16 +62,16 @@ python -m rl_zoo3.push_to_hub --algo dqn --env SpaceInvadersNoFrameskip-v4 -f lo
62
 
63
  ## Hyperparameters
64
  ```python
65
- OrderedDict([('batch_size', 1024),
66
  ('buffer_size', 100000),
67
  ('env_wrapper',
68
  ['stable_baselines3.common.atari_wrappers.AtariWrapper']),
69
  ('exploration_final_eps', 0.01),
70
- ('exploration_fraction', 0.025),
71
  ('frame_stack', 4),
72
  ('gradient_steps', 1),
73
- ('learning_rate', 0.0001),
74
- ('learning_starts', 10000),
75
  ('n_timesteps', 1000000.0),
76
  ('optimize_memory_usage', False),
77
  ('policy', 'CnnPolicy'),
 
16
  type: SpaceInvadersNoFrameskip-v4
17
  metrics:
18
  - type: mean_reward
19
+ value: 439.50 +/- 160.10
20
  name: mean_reward
21
  verified: false
22
  ---
 
62
 
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', 5e-05),
74
+ ('learning_starts', 100000),
75
  ('n_timesteps', 1000000.0),
76
  ('optimize_memory_usage', False),
77
  ('policy', 'CnnPolicy'),
args.yml CHANGED
@@ -54,7 +54,7 @@
54
  - - save_replay_buffer
55
  - false
56
  - - seed
57
- - 265090744
58
  - - storage
59
  - null
60
  - - study_name
 
54
  - - save_replay_buffer
55
  - false
56
  - - seed
57
+ - 2950847451
58
  - - storage
59
  - null
60
  - - study_name
config.yml CHANGED
@@ -1,6 +1,6 @@
1
  !!python/object/apply:collections.OrderedDict
2
  - - - batch_size
3
- - 1024
4
  - - buffer_size
5
  - 100000
6
  - - env_wrapper
@@ -8,15 +8,15 @@
8
  - - exploration_final_eps
9
  - 0.01
10
  - - exploration_fraction
11
- - 0.025
12
  - - frame_stack
13
  - 4
14
  - - gradient_steps
15
  - 1
16
  - - learning_rate
17
- - 0.0001
18
  - - learning_starts
19
- - 10000
20
  - - n_timesteps
21
  - 1000000.0
22
  - - optimize_memory_usage
 
1
  !!python/object/apply:collections.OrderedDict
2
  - - - batch_size
3
+ - 32
4
  - - buffer_size
5
  - 100000
6
  - - env_wrapper
 
8
  - - exploration_final_eps
9
  - 0.01
10
  - - exploration_fraction
11
+ - 0.1
12
  - - frame_stack
13
  - 4
14
  - - gradient_steps
15
  - 1
16
  - - learning_rate
17
+ - 5.0e-05
18
  - - learning_starts
19
+ - 100000
20
  - - n_timesteps
21
  - 1000000.0
22
  - - optimize_memory_usage
dqn-SpaceInvadersNoFrameskip-v4.zip CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:631f377061bbe104afe5783aeef3d9f4baec192b586baecf92c644feb1c4b1da
3
- size 27220145
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:957236f18d3e3f30047ed00f3c209f1bc93a56d0d72904da34f9df381a356386
3
+ size 27219567
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 sha256:6087e71397fd9c75ee574d9f4cc334904c0e051a0cc44f33b33eeb2c7946070b
3
- size 13506236
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dbdc0786aa251991a7ce281a95eb737abd9f82f502614cc284716facf26622db
3
+ size 13505852
dqn-SpaceInvadersNoFrameskip-v4/policy.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:800b917b9a9178db8a3d33c4fa92e74b2a86a375b8b5e6dce9586943d8b968f9
3
- size 13505370
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0c3483fbd54e25077af91ddda75375a05bbb4f7de881642df93ad05180358478
3
+ size 13505178
dqn-SpaceInvadersNoFrameskip-v4/system_info.txt CHANGED
@@ -2,7 +2,7 @@
2
  - Python: 3.10.12
3
  - Stable-Baselines3: 2.3.0a2
4
  - PyTorch: 2.2.1+cu121
5
- - GPU Enabled: True
6
  - Numpy: 1.26.4
7
  - Cloudpickle: 3.0.0
8
  - Gymnasium: 0.29.1
 
2
  - Python: 3.10.12
3
  - Stable-Baselines3: 2.3.0a2
4
  - PyTorch: 2.2.1+cu121
5
+ - GPU Enabled: False
6
  - Numpy: 1.26.4
7
  - Cloudpickle: 3.0.0
8
  - Gymnasium: 0.29.1
replay.mp4 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:767c4e20c0d9b64b4c168ca2032209c82a40398f96ac64aeb21439829410c005
3
- size 245193
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:09b62df74873f116319719d1db42d488af1e87b579d5f8537042955d6add0416
3
+ size 219308
results.json CHANGED
@@ -1 +1 @@
1
- {"mean_reward": 401.5, "std_reward": 239.4269199568002, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2024-02-27T15:17:29.785296"}
 
1
+ {"mean_reward": 439.5, "std_reward": 160.10074952978826, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2024-02-27T19:51:07.021708"}
train_eval_metrics.zip CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7119cd1f7a617469a4b69042d57e7b993518b3c08264157df6f162f60144b5b4
3
- size 41098
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5b65e028ee4bce23630c333ecbc0a5fda0782023ec966a7f85617beab03be66d
3
+ size 41027