Hugging Face's logo

kforkai
/
dqn-SpaceInvadersNoFrameskip-v4

Reinforcement Learning
stable-baselines3
SpaceInvadersNoFrameskip-v4
deep-reinforcement-learning
Eval Results (legacy)
Model card Files
xet
 Community
kforkai commited on
Commit
f6c0747
·
1 Parent(s): fad2243

Initial commit

Browse files
Files changed (10) hide show
  1. README.md +3 -3
  2. args.yml +1 -1
  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 +2 -2
  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: 257.00 +/- 38.81
20
  name: mean_reward
21
  verified: false
22
  ---
@@ -70,9 +70,9 @@ OrderedDict([('batch_size', 32),
70
  ('exploration_fraction', 0.1),
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'),
78
  ('target_update_interval', 1000),
 
16
  type: SpaceInvadersNoFrameskip-v4
17
  metrics:
18
  - type: mean_reward
19
+ value: 352.00 +/- 98.65
20
  name: mean_reward
21
  verified: false
22
  ---
 
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),
76
  ('optimize_memory_usage', False),
77
  ('policy', 'CnnPolicy'),
78
  ('target_update_interval', 1000),
args.yml CHANGED
@@ -54,7 +54,7 @@
54
  - - save_replay_buffer
55
  - false
56
  - - seed
57
- - 761678430
58
  - - storage
59
  - null
60
  - - study_name
 
54
  - - save_replay_buffer
55
  - false
56
  - - seed
57
+ - 2746942509
58
  - - storage
59
  - null
60
  - - study_name
config.yml CHANGED
@@ -14,11 +14,11 @@
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
23
  - false
24
  - - policy
 
14
  - - gradient_steps
15
  - 1
16
  - - learning_rate
17
+ - 0.0001
18
  - - learning_starts
19
  - 100000
20
  - - n_timesteps
21
+ - 500000
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 sha256:409b564beb5b58b772371c8206d3d2dc1b12b13ddd7dea04b5cbcd7724dc4356
3
- size 13713331
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9ff9dbfc3ee7436adbda40c3c98c2395e2ed20f7f6a96eeb927ff178234b99a7
3
+ size 27218389
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 sha256:0deb940c86ab5538de5b7bd48f2a3305a3491099536c85fbff2bf1588b36f07a
3
- size 687
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eadac486c915230f19a756019dd0ac04fd1276da26cdf3838b5011c1bdceae18
3
+ size 13505739
dqn-SpaceInvadersNoFrameskip-v4/policy.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:97acaf67daef1cba3d509306b7bdc4f1659b0bb05b6bf21c75c0fa03c03c9349
3
  size 13504937
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1c458357216e52da61b608f8cc0eb49f8dbb54c97b41d3f3e3a9639a8011c182
3
  size 13504937
replay.mp4 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:639ed24f99a933f1e1ec6641ac3cdb60d5af53346f4284f5e005616c88bda87c
3
- size 267918
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1827d4ce0404deb2e29bf27c94a6ad37e524ea0f744103244180a01ac89f0f50
3
+ size 266886
results.json CHANGED
@@ -1 +1 @@
1
- {"mean_reward": 257.0, "std_reward": 38.80721582386451, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2023-06-06T14:43:28.836079"}
 
1
+ {"mean_reward": 352.0, "std_reward": 98.6458311334037, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2023-06-06T15:24:26.358046"}
train_eval_metrics.zip CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:89c9243e2eb90c2478610960d0bdbd7620fe30b191674eea84b5b3aef806a82e
3
- size 5694
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2eee5816553c15de21bc34f96de1e1cbc94da1005ccabf664e7305714b71879c
3
+ size 21913