Hugging Face's logo

MattStammers
/
dqn-QbertNoFrameskip-v4

Reinforcement Learning
stable-baselines3
QbertNoFrameskip-v4
deep-reinforcement-learning
Eval Results
Model card Files Community
MattStammers commited on
Commit
4bad67c
•
1 Parent(s): fc27504

Initial commit

Browse files
Files changed (9) hide show
  1. README.md +1 -1
  2. args.yml +1 -1
  3. dqn-QbertNoFrameskip-v4.zip +2 -2
  4. dqn-QbertNoFrameskip-v4/data +0 -0
  5. dqn-QbertNoFrameskip-v4/policy.optimizer.pth +1 -1
  6. dqn-QbertNoFrameskip-v4/policy.pth +1 -1
  7. replay.mp4 +2 -2
  8. results.json +1 -1
  9. train_eval_metrics.zip +2 -2
README.md CHANGED
@@ -16,7 +16,7 @@ model-index:
16
  type: QbertNoFrameskip-v4
17
  metrics:
18
  - type: mean_reward
19
- value: 1430.00 +/- 1324.85
20
  name: mean_reward
21
  verified: false
22
  ---
 
16
  type: QbertNoFrameskip-v4
17
  metrics:
18
  - type: mean_reward
19
+ value: 9365.00 +/- 4858.69
20
  name: mean_reward
21
  verified: false
22
  ---
args.yml CHANGED
@@ -54,7 +54,7 @@
54
  - - save_replay_buffer
55
  - false
56
  - - seed
57
- - 3297263248
58
  - - storage
59
  - null
60
  - - study_name
 
54
  - - save_replay_buffer
55
  - false
56
  - - seed
57
+ - 2244660574
58
  - - storage
59
  - null
60
  - - study_name
dqn-QbertNoFrameskip-v4.zip CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6d25640cab9f9075ff5782bf138d4c94a80ab4737d0c4b25ab883498c254b296
3
- size 27217854
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:65613701f9dec17f358574d5f843342d7ebf612324350294a60b5d4fe3278ebf
3
+ size 27217851
dqn-QbertNoFrameskip-v4/data CHANGED
The diff for this file is too large to render. See raw diff
 
dqn-QbertNoFrameskip-v4/policy.optimizer.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e4becc26e18883a1a20c07ef7f59c297d768304c210cdf5b32bff6534387e07e
3
  size 13505419
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bca8868c476f081908c21f2511b93dbe73b4427b491947b41499faa2a6d177be
3
  size 13505419
dqn-QbertNoFrameskip-v4/policy.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:cef34a63a97d8a3c6095819db92e8676202912fbec940b1b60f676bae5875d39
3
  size 13504745
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3671ccfd83d1799aca8569afc583310afc7e1e6650957fad8051cc10ce3b458f
3
  size 13504745
replay.mp4 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:056f3e342985e3ffeb488dbaf427c283514dc37976273b71f33030559ea41e2f
3
- size 164898
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2ba4ac76b08a4cd82d52fd38324ad530e857c83089decb9cba64092db1fa9500
3
+ size 213172
results.json CHANGED
@@ -1 +1 @@
1
- {"mean_reward": 1430.0, "std_reward": 1324.8490480050925, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2023-08-22T11:10:47.859306"}
 
1
+ {"mean_reward": 9365.0, "std_reward": 4858.693239956604, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2023-08-23T07:09:17.168055"}
train_eval_metrics.zip CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:70299bf9e025cf8739f94ce1dd2b27becc020acc64050c542ab15ced5c1d354a
3
- size 82669
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:868ae496b996e99da527e05a15dcc1416509a82ca4d03dc3b50c97bbec5cbe3d
3
+ size 355830