Hugging Face's logo

mryoshq
/
dqn-SpaceInvadersNoFrameskip-v4

Reinforcement Learning
stable-baselines3
SpaceInvadersNoFrameskip-v4
deep-reinforcement-learning
Eval Results
Model card Files Community
mryoshq commited on
Commit
b99d2ac
•
1 Parent(s): 0565b43

Initial commit

Browse files
Files changed (10) hide show
  1. README.md +2 -2
  2. args.yml +2 -2
  3. config.yml +1 -1
  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: 329.00 +/- 157.97
20
  name: mean_reward
21
  verified: false
22
  ---
@@ -72,7 +72,7 @@ OrderedDict([('batch_size', 32),
72
  ('gradient_steps', 1),
73
  ('learning_rate', 0.0001),
74
  ('learning_starts', 100000),
75
- ('n_timesteps', 100000.0),
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: 700.00 +/- 154.58
20
  name: mean_reward
21
  verified: false
22
  ---
 
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),
args.yml CHANGED
@@ -2,7 +2,7 @@
2
  - - - algo
3
  - dqn
4
  - - conf_file
5
- - dqn.yml
6
  - - device
7
  - auto
8
  - - env
@@ -54,7 +54,7 @@
54
  - - save_replay_buffer
55
  - false
56
  - - seed
57
- - 2997901264
58
  - - storage
59
  - null
60
  - - study_name
 
2
  - - - algo
3
  - dqn
4
  - - conf_file
5
+ - /content/dqn.yml
6
  - - device
7
  - auto
8
  - - env
 
54
  - - save_replay_buffer
55
  - false
56
  - - seed
57
+ - 2140663166
58
  - - storage
59
  - null
60
  - - study_name
config.yml CHANGED
@@ -18,7 +18,7 @@
18
  - - learning_starts
19
  - 100000
20
  - - n_timesteps
21
- - 100000.0
22
  - - optimize_memory_usage
23
  - false
24
  - - policy
 
18
  - - learning_starts
19
  - 100000
20
  - - n_timesteps
21
+ - 1000000.0
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 sha256:1f33480989df2303439c11a335aafe6e8c43231082a5262c52b540660cca2a2e
3
- size 13715011
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2fa92a755b575a529fb9a1efbfbb10d1a554396bd7d697d602b26b0b7ec8c52a
3
+ size 27220136
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 sha256:57d6a8865f572577ebde3a14c96d5df65db82d4ac06366403ab0b89742f26734
3
+ size 13506236
dqn-SpaceInvadersNoFrameskip-v4/policy.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:030bbec757b031b2ba7d7cb7777bd0821571e80ffa56b3874349a92f30865541
3
  size 13505370
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d4b91a754800ce114d433387d0cbc6511f45dc068fcf7690fe0a61ef2fa9bd2d
3
  size 13505370
replay.mp4 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:99e402fa68302f9262ebfd7be784ce6ff6785b68f25d4aa3a86e2c515a7bbb11
3
- size 242628
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9cc94ec803d6c0fc36a0c3212e68aa8daab8415e23e1d55064b506e16e51b1ed
3
+ size 210251
results.json CHANGED
@@ -1 +1 @@
1
- {"mean_reward": 329.0, "std_reward": 157.96835126062436, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2024-01-19T18:45:38.424679"}
 
1
+ {"mean_reward": 700.0, "std_reward": 154.58007633585902, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2024-02-12T22:59:57.976509"}
train_eval_metrics.zip CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a2bfae44045d1e7c9cc384d1c6ab12834d13ad51ff0655d29abc370fcd251ef9
3
- size 5899
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6f511b1602c59061b50b504c1889e2d42f13b72453513ba3b0a82cf55bf02767
3
+ size 36817