Hugging Face's logo

sinny
/
unit3_si

Reinforcement Learning
stable-baselines3
SpaceInvadersNoFrameskip-v4
deep-reinforcement-learning
Eval Results (legacy)
Model card Files
xet
Community
sinny commited on
Commit
9cef2bc
·
1 Parent(s): 82383ca

Initial commit

Browse files
Files changed (10) hide show
  1. README.md +3 -3
  2. args.yml +6 -6
  3. config.yml +2 -2
  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: 219.50 +/- 79.54
20
  name: mean_reward
21
  verified: false
22
  ---
@@ -62,7 +62,7 @@ python -m rl_zoo3.push_to_hub --algo dqn --env SpaceInvadersNoFrameskip-v4 -f lo
62
 
63
  ## Hyperparameters
64
  ```python
65
- OrderedDict([('batch_size', 2048),
66
  ('buffer_size', 100000),
67
  ('env_wrapper',
68
  ['stable_baselines3.common.atari_wrappers.AtariWrapper']),
@@ -76,6 +76,6 @@ OrderedDict([('batch_size', 2048),
76
  ('optimize_memory_usage', False),
77
  ('policy', 'CnnPolicy'),
78
  ('target_update_interval', 1000),
79
- ('train_freq', 10),
80
  ('normalize', False)])
81
  ```
 
16
  type: SpaceInvadersNoFrameskip-v4
17
  metrics:
18
  - type: mean_reward
19
+ value: 162.00 +/- 97.52
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']),
 
76
  ('optimize_memory_usage', False),
77
  ('policy', 'CnnPolicy'),
78
  ('target_update_interval', 1000),
79
+ ('train_freq', 4),
80
  ('normalize', False)])
81
  ```
args.yml CHANGED
@@ -4,7 +4,7 @@
4
  - - conf_file
5
  - null
6
  - - device
7
- - cuda
8
  - - env
9
  - SpaceInvadersNoFrameskip-v4
10
  - - env_kwargs
@@ -24,11 +24,11 @@
24
  - - max_total_trials
25
  - null
26
  - - n_eval_envs
27
- - 8
28
  - - n_evaluations
29
  - null
30
  - - n_jobs
31
- - 8
32
  - - n_startup_trials
33
  - 10
34
  - - n_timesteps
@@ -38,7 +38,7 @@
38
  - - no_optim_plots
39
  - false
40
  - - num_threads
41
- - 14
42
  - - optimization_log_path
43
  - null
44
  - - optimize_hyperparameters
@@ -54,13 +54,13 @@
54
  - - save_replay_buffer
55
  - false
56
  - - seed
57
- - 3843453937
58
  - - storage
59
  - null
60
  - - study_name
61
  - null
62
  - - tensorboard_log
63
- - logs/
64
  - - track
65
  - false
66
  - - trained_agent
 
4
  - - conf_file
5
  - null
6
  - - device
7
+ - auto
8
  - - env
9
  - SpaceInvadersNoFrameskip-v4
10
  - - env_kwargs
 
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
 
38
  - - no_optim_plots
39
  - false
40
  - - num_threads
41
+ - -1
42
  - - optimization_log_path
43
  - null
44
  - - optimize_hyperparameters
 
54
  - - save_replay_buffer
55
  - false
56
  - - seed
57
+ - 58689742
58
  - - storage
59
  - null
60
  - - study_name
61
  - null
62
  - - tensorboard_log
63
+ - ''
64
  - - track
65
  - false
66
  - - trained_agent
config.yml CHANGED
@@ -1,6 +1,6 @@
1
  !!python/object/apply:collections.OrderedDict
2
  - - - batch_size
3
- - 2048
4
  - - buffer_size
5
  - 100000
6
  - - env_wrapper
@@ -26,4 +26,4 @@
26
  - - target_update_interval
27
  - 1000
28
  - - train_freq
29
- - 10
 
1
  !!python/object/apply:collections.OrderedDict
2
  - - - batch_size
3
+ - 32
4
  - - buffer_size
5
  - 100000
6
  - - env_wrapper
 
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 sha256:3bbe8956ccb93a609bee15a3b08fee6b78ddbc811f1c26062f1c9d5a098a5f32
3
- size 27225070
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:89ababbeb4901c7ebbd0caff6e36d20af8185a88486a807d4f77c7760d617b29
3
+ size 27225035
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 sha256:363b068b36e8b0683a5000d7000a1453353e7d0c7a0fdf7e6aed02aff05f3536
3
  size 13505739
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:19d99ce18ae2d43c7bbdd6352f8d7e8b2f232d552a63556cf8cd5caccca75bd3
3
  size 13505739
dqn-SpaceInvadersNoFrameskip-v4/policy.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a3cf05dbd3a53152ae3c9754d4029b12ca30526946d3f586cd70d9d0f74e420d
3
  size 13504937
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:154985944c34fef31c093eef67c90ae9bb21e7aaf943bbfc543e907007e7ec87
3
  size 13504937
replay.mp4 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:bb3ec1c97c3d10676bcf4cd18c944380f344f0f64a7bdacbf8b30eb59923abef
3
- size 256808
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9839ae0dc36272b44bae9f84076607c5a5a818adb7a22f7680bf9956b5df622e
3
+ size 257163
results.json CHANGED
@@ -1 +1 @@
1
- {"mean_reward": 219.5, "std_reward": 79.54401297395047, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2023-01-15T10:32:48.071562"}
 
1
+ {"mean_reward": 162.0, "std_reward": 97.52435593224905, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2023-01-15T10:52:33.215576"}
train_eval_metrics.zip CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0ed225278689463405af18cb36d1ac245e1dd44041058b3c062f988ea6f2b081
3
- size 12362
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8a85e8334f925941a6f7d0dd6ae85e98cb101ab6332129e36c8b5474626a94a2
3
+ size 5817