Hugging Face's logo

Dewa
/
dqn-SpaceInvadersNoFrameskip-v4-version-6

Reinforcement Learning
stable-baselines3
SpaceInvadersNoFrameskip-v4
deep-reinforcement-learning
Eval Results
Model card Files Community
Dewa commited on
Commit
287d88c
•
1 Parent(s): 5c68723

Initial commit

Browse files
Files changed (8) hide show
  1. README.md +1 -1
  2. args.yml +2 -2
  3. dqn-SpaceInvadersNoFrameskip-v4.zip +2 -2
  4. dqn-SpaceInvadersNoFrameskip-v4/data +0 -0
  5. dqn-SpaceInvadersNoFrameskip-v4/policy.pth +1 -1
  6. replay.mp4 +2 -2
  7. results.json +1 -1
  8. 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: 14.50 +/- 12.34
20
  name: mean_reward
21
  verified: false
22
  ---
 
16
  type: SpaceInvadersNoFrameskip-v4
17
  metrics:
18
  - type: mean_reward
19
+ value: 274.50 +/- 31.50
20
  name: mean_reward
21
  verified: false
22
  ---
args.yml CHANGED
@@ -32,7 +32,7 @@
32
  - - n_startup_trials
33
  - 10
34
  - - n_timesteps
35
- - 10000
36
  - - n_trials
37
  - 500
38
  - - no_optim_plots
@@ -54,7 +54,7 @@
54
  - - save_replay_buffer
55
  - false
56
  - - seed
57
- - 1133060681
58
  - - storage
59
  - null
60
  - - study_name
 
32
  - - n_startup_trials
33
  - 10
34
  - - n_timesteps
35
+ - 50000
36
  - - n_trials
37
  - 500
38
  - - no_optim_plots
 
54
  - - save_replay_buffer
55
  - false
56
  - - seed
57
+ - 1650781472
58
  - - storage
59
  - null
60
  - - study_name
dqn-SpaceInvadersNoFrameskip-v4.zip CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:36064871b68b618ee1ff4d8484b5b64165e34a4da260561526c1c7ae31568ec7
3
- size 13716430
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c65d4ae99b8b4bc0e40e1052c05d45a660f8a5ef0778a370e342ec6e9b36eaaf
3
+ size 13719611
dqn-SpaceInvadersNoFrameskip-v4/data CHANGED
The diff for this file is too large to render. See raw diff
 
dqn-SpaceInvadersNoFrameskip-v4/policy.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:69e804349df40c380f834f8af7cb1fe21ea5263b1c99444df17aec6bc2c71987
3
  size 13504937
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8e5118cd29fd228dbd5eca340830c980bf3c12140ca9d01173570dfcb76a21aa
3
  size 13504937
replay.mp4 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3fed103c47817f3f94ef4564da11c292e2891460f38d04aed7c8ce7eca6e1ea9
3
- size 275554
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fba2ab7031f7061f065c3d5bc1de3dcfb9536d40b9bccd2413c48c7909f59ea3
3
+ size 261744
results.json CHANGED
@@ -1 +1 @@
1
- {"mean_reward": 14.5, "std_reward": 12.338962679253067, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2023-04-26T13:08:24.611571"}
 
1
+ {"mean_reward": 274.5, "std_reward": 31.5, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2023-04-26T13:39:41.226938"}
train_eval_metrics.zip CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7c8041f939048131d8fbccecb8e0f0e6b1cf0f910b24dd10988c3dfe41f9a004
3
- size 610
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:372c73a0eea12ebc6d9d77fd07fe7ef4dc175a9ec1c706efc9bc10ccd5d73f52
3
+ size 3334