Hugging Face's logo

Rudolph314
/
dqn-SpaceInvadersNoFrameskip-v4

Reinforcement Learning
stable-baselines3
SpaceInvadersNoFrameskip-v4
deep-reinforcement-learning
Eval Results
Model card Files Community
Rudolph314 commited on
Commit
c9a6fab
•
1 Parent(s): 9820512

Initial commit

Browse files
Files changed (11) hide show
  1. README.md +6 -5
  2. args.yml +81 -81
  3. config.yml +31 -29
  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: 170.00 +/- 96.72
20
  name: mean_reward
21
  verified: false
22
  ---
@@ -62,21 +62,22 @@ python -m rl_zoo3.push_to_hub --algo dqn --env SpaceInvadersNoFrameskip-v4 -f lo
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', 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
  ```
82
 
 
16
  type: SpaceInvadersNoFrameskip-v4
17
  metrics:
18
  - type: mean_reward
19
+ value: 279.00 +/- 141.93
20
  name: mean_reward
21
  verified: false
22
  ---
 
62
 
63
  ## Hyperparameters
64
  ```python
65
+ OrderedDict([('batch_size', 128),
66
  ('buffer_size', 100000),
67
  ('env_wrapper',
68
  ['stable_baselines3.common.atari_wrappers.AtariWrapper']),
69
  ('exploration_final_eps', 0.01),
70
+ ('exploration_fraction', 0.2),
71
+ ('exploration_initial_eps', 0.8),
72
  ('frame_stack', 4),
73
  ('gradient_steps', 1),
74
+ ('learning_rate', 0.0005),
75
  ('learning_starts', 100000),
76
  ('n_timesteps', 1000000.0),
77
  ('optimize_memory_usage', False),
78
  ('policy', 'CnnPolicy'),
79
  ('target_update_interval', 1000),
80
+ ('train_freq', 8),
81
  ('normalize', False)])
82
  ```
83
 
args.yml CHANGED
@@ -1,81 +1,81 @@
1
- !!python/object/apply:collections.OrderedDict
2
- - - - algo
3
- - dqn
4
- - - conf_file
5
- - dqn.yml
6
- - - device
7
- - auto
8
- - - env
9
- - SpaceInvadersNoFrameskip-v4
10
- - - env_kwargs
11
- - null
12
- - - eval_episodes
13
- - 5
14
- - - eval_freq
15
- - 25000
16
- - - gym_packages
17
- - []
18
- - - hyperparams
19
- - null
20
- - - log_folder
21
- - content/drive/MyDrive/logs/
22
- - - log_interval
23
- - -1
24
- - - max_total_trials
25
- - null
26
- - - n_eval_envs
27
- - 1
28
- - - n_evaluations
29
- - null
30
- - - n_jobs
31
- - 1
32
- - - n_startup_trials
33
- - 10
34
- - - n_timesteps
35
- - -1
36
- - - n_trials
37
- - 500
38
- - - no_optim_plots
39
- - false
40
- - - num_threads
41
- - -1
42
- - - optimization_log_path
43
- - null
44
- - - optimize_hyperparameters
45
- - false
46
- - - progress
47
- - false
48
- - - pruner
49
- - median
50
- - - sampler
51
- - tpe
52
- - - save_freq
53
- - -1
54
- - - save_replay_buffer
55
- - false
56
- - - seed
57
- - 3452325604
58
- - - storage
59
- - null
60
- - - study_name
61
- - null
62
- - - tensorboard_log
63
- - ''
64
- - - track
65
- - false
66
- - - trained_agent
67
- - ''
68
- - - truncate_last_trajectory
69
- - true
70
- - - uuid
71
- - false
72
- - - vec_env
73
- - dummy
74
- - - verbose
75
- - 1
76
- - - wandb_entity
77
- - null
78
- - - wandb_project_name
79
- - sb3
80
- - - wandb_tags
81
- - []
 
1
+ !!python/object/apply:collections.OrderedDict
2
+ - - - algo
3
+ - dqn
4
+ - - conf_file
5
+ - dqn.yml
6
+ - - device
7
+ - auto
8
+ - - env
9
+ - SpaceInvadersNoFrameskip-v4
10
+ - - env_kwargs
11
+ - null
12
+ - - eval_episodes
13
+ - 5
14
+ - - eval_freq
15
+ - 25000
16
+ - - gym_packages
17
+ - []
18
+ - - hyperparams
19
+ - null
20
+ - - log_folder
21
+ - logs/
22
+ - - log_interval
23
+ - -1
24
+ - - max_total_trials
25
+ - null
26
+ - - n_eval_envs
27
+ - 1
28
+ - - n_evaluations
29
+ - null
30
+ - - n_jobs
31
+ - 1
32
+ - - n_startup_trials
33
+ - 10
34
+ - - n_timesteps
35
+ - -1
36
+ - - n_trials
37
+ - 500
38
+ - - no_optim_plots
39
+ - false
40
+ - - num_threads
41
+ - -1
42
+ - - optimization_log_path
43
+ - null
44
+ - - optimize_hyperparameters
45
+ - false
46
+ - - progress
47
+ - false
48
+ - - pruner
49
+ - median
50
+ - - sampler
51
+ - tpe
52
+ - - save_freq
53
+ - -1
54
+ - - save_replay_buffer
55
+ - false
56
+ - - seed
57
+ - 3441574639
58
+ - - storage
59
+ - null
60
+ - - study_name
61
+ - null
62
+ - - tensorboard_log
63
+ - ''
64
+ - - track
65
+ - false
66
+ - - trained_agent
67
+ - ''
68
+ - - truncate_last_trajectory
69
+ - true
70
+ - - uuid
71
+ - false
72
+ - - vec_env
73
+ - dummy
74
+ - - verbose
75
+ - 1
76
+ - - wandb_entity
77
+ - null
78
+ - - wandb_project_name
79
+ - sb3
80
+ - - wandb_tags
81
+ - []
config.yml CHANGED
@@ -1,29 +1,31 @@
1
- !!python/object/apply:collections.OrderedDict
2
- - - - batch_size
3
- - 32
4
- - - buffer_size
5
- - 100000
6
- - - env_wrapper
7
- - - stable_baselines3.common.atari_wrappers.AtariWrapper
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
- - 0.0001
18
- - - learning_starts
19
- - 100000
20
- - - n_timesteps
21
- - 1000000.0
22
- - - optimize_memory_usage
23
- - false
24
- - - policy
25
- - CnnPolicy
26
- - - target_update_interval
27
- - 1000
28
- - - train_freq
29
- - 4
 
 
 
1
+ !!python/object/apply:collections.OrderedDict
2
+ - - - batch_size
3
+ - 128
4
+ - - buffer_size
5
+ - 100000
6
+ - - env_wrapper
7
+ - - stable_baselines3.common.atari_wrappers.AtariWrapper
8
+ - - exploration_final_eps
9
+ - 0.01
10
+ - - exploration_fraction
11
+ - 0.2
12
+ - - exploration_initial_eps
13
+ - 0.8
14
+ - - frame_stack
15
+ - 4
16
+ - - gradient_steps
17
+ - 1
18
+ - - learning_rate
19
+ - 0.0005
20
+ - - learning_starts
21
+ - 100000
22
+ - - n_timesteps
23
+ - 1000000.0
24
+ - - optimize_memory_usage
25
+ - false
26
+ - - policy
27
+ - CnnPolicy
28
+ - - target_update_interval
29
+ - 1000
30
+ - - train_freq
31
+ - 8
dqn-SpaceInvadersNoFrameskip-v4.zip CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:55345be50deaf4be80c8435d1f4aea2436eb8e8346272ad313ab7c64e0da6eca
3
- size 13712093
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b0fdb061bec62cb83dd72a0271a9a3fbf0b8ec2cbbeb78baf2a548886e21f6a4
3
+ size 27219177
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:e3fc84919e676e2bdcaa04814c7dfa2b7625d8d53a818418c6db25771364db93
3
- size 1120
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b1af54039a8fa89b73c77ac969c44d9c4d7cb75da4e3993d158991dd10583fd8
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:c35b631c4b958faa3101feb2c56d21bb2f961882a12f7eaec4592d5edbd2fd52
3
- size 13505178
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b6779c4bbb850b5496130efbcac7f6c305d0e5402cef2a164e1600093717cdb6
3
+ size 13505370
dqn-SpaceInvadersNoFrameskip-v4/system_info.txt CHANGED
@@ -2,7 +2,7 @@
2
  - Python: 3.10.12
3
  - Stable-Baselines3: 2.3.0
4
  - PyTorch: 2.2.1+cu121
5
- - GPU Enabled: False
6
  - Numpy: 1.25.2
7
  - Cloudpickle: 2.2.1
8
  - Gymnasium: 0.29.1
 
2
  - Python: 3.10.12
3
  - Stable-Baselines3: 2.3.0
4
  - PyTorch: 2.2.1+cu121
5
+ - GPU Enabled: True
6
  - Numpy: 1.25.2
7
  - Cloudpickle: 2.2.1
8
  - Gymnasium: 0.29.1
replay.mp4 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:59e7e865d2ae4d0b2fe6b63de61e9e4792e48e174d3f74e8405897dace698287
3
- size 263639
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:85d65b28ac6e79cf508ccea4e006c3b1397ba20fb086169339707c16d6586d06
3
+ size 233056
results.json CHANGED
@@ -1 +1 @@
1
- {"mean_reward": 170.0, "std_reward": 96.7212489580237, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2024-04-11T03:16:34.191262"}
 
1
+ {"mean_reward": 279.0, "std_reward": 141.92955999368138, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2024-04-12T03:01:55.745656"}
train_eval_metrics.zip CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:37a6fe1d04f08119c15000156af9e812f7b5ecf62f740903ef1862f5f2f4461f
3
- size 893
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:745fecfb5fd94724a45c31500593dfb169ea6111d134f2d25f9c96842b932043
3
+ size 34341