Hugging Face's logo

cmattoon
/
dqn-SpaceInvadersNoFrameskip-v4

Reinforcement Learning
stable-baselines3
SpaceInvadersNoFrameskip-v4
deep-reinforcement-learning
Eval Results
Model card Files Community
cmattoon commited on
Commit
bbebfde
•
1 Parent(s): 515bb31

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: 268.00 +/- 147.63
20
  name: mean_reward
21
  verified: false
22
  ---
@@ -70,9 +70,9 @@ OrderedDict([('batch_size', 256),
70
  ('exploration_fraction', 0.05),
71
  ('frame_stack', 4),
72
  ('gradient_steps', 1),
73
- ('learning_rate', 1.722e-05),
74
  ('learning_starts', 100000),
75
- ('n_timesteps', 200000.0),
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: 312.00 +/- 164.35
20
  name: mean_reward
21
  verified: false
22
  ---
 
70
  ('exploration_fraction', 0.05),
71
  ('frame_stack', 4),
72
  ('gradient_steps', 1),
73
+ ('learning_rate', 0.0001722),
74
  ('learning_starts', 100000),
75
+ ('n_timesteps', 100000.0),
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
- - 3659123133
58
  - - storage
59
  - null
60
  - - study_name
 
54
  - - save_replay_buffer
55
  - false
56
  - - seed
57
+ - 1754488008
58
  - - storage
59
  - null
60
  - - study_name
config.yml CHANGED
@@ -14,11 +14,11 @@
14
  - - gradient_steps
15
  - 1
16
  - - learning_rate
17
- - 1.722e-05
18
  - - learning_starts
19
  - 100000
20
  - - n_timesteps
21
- - 200000.0
22
  - - optimize_memory_usage
23
  - false
24
  - - policy
 
14
  - - gradient_steps
15
  - 1
16
  - - learning_rate
17
+ - 0.0001722
18
  - - learning_starts
19
  - 100000
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 sha256:5c670bf85804d6e80fee206b8bcdec22290b668497e94abe114443520e00f949
3
- size 27220788
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f36f19735066e4ae3b301e864eaa6a9abd37dd958d2c761aa5c06ac382b9a195
3
+ size 13715667
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 sha256:41585380875df7fd4085abd5ea1c3840bb35080fa35792f98ef262cb46e057d4
3
- size 13506236
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2eebf306119e31fc0bc923cc0e9a9d1101f70e8b9107b805dfb48b63c0921510
3
+ size 1120
dqn-SpaceInvadersNoFrameskip-v4/policy.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:cef4740f4d735cbbb0b6776aefb3489330e1f52177bc055a2a3c46b607ca4c4b
3
  size 13505370
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8c42d0c2e87f9cfa7890772461712b0a3c77703d342de35e7e29361818b8acda
3
  size 13505370
replay.mp4 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0f69d56168031ab968810c88d65c19bdc281baf0751a9007ab674a111030b91d
3
- size 274727
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a36e3fe8961766ab38dda9750258eb43e0a871a98ac02992ffa42fdd8756b529
3
+ size 247208
results.json CHANGED
@@ -1 +1 @@
1
- {"mean_reward": 268.0, "std_reward": 147.63468427168462, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2024-04-25T02:54:20.994838"}
 
1
+ {"mean_reward": 312.0, "std_reward": 164.3502357771354, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2024-04-25T03:04:17.293336"}
train_eval_metrics.zip CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:43fac3dbd3a33fea4df470893668116895a67b1dfafeef79a5456faea164ac39
3
- size 9732
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ecccca310e121fe6fe28e6711ce1ca30ca03f1e22b97af0d521d4a18a38e1300
3
+ size 5576