Hugging Face's logo

RegisGraptin
/
a2c-PandaPushDense-v2

Reinforcement Learning
stable-baselines3
PandaPushDense-v2
deep-reinforcement-learning
Eval Results
Model card Files Community
1
RegisGraptin commited on
Commit
97dfe42
·
1 Parent(s): bf1f7df

Initial commit

Browse files
Files changed (5) hide show
  1. README.md +1 -1
  2. a2c-PandaPushDense-v2.zip +1 -1
  3. replay.mp4 +0 -0
  4. results.json +1 -1
  5. vec_normalize.pkl +1 -1
README.md CHANGED
@@ -16,7 +16,7 @@ model-index:
16
  type: PandaPushDense-v2
17
  metrics:
18
  - type: mean_reward
19
- value: -8.84 +/- 4.76
20
  name: mean_reward
21
  verified: false
22
  ---
 
16
  type: PandaPushDense-v2
17
  metrics:
18
  - type: mean_reward
19
+ value: -7.97 +/- 5.48
20
  name: mean_reward
21
  verified: false
22
  ---
a2c-PandaPushDense-v2.zip CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0d13dfba3808a78a91b9e504243e4d4a16a541b6fe96359d21d7bb867f0b7a97
3
  size 123674
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:524d09d28ee215910defc2f60c0ed2437b3e75fc14af29b2214d31a3b554555d
3
  size 123674
replay.mp4 CHANGED
Binary files a/replay.mp4 and b/replay.mp4 differ
 
results.json CHANGED
@@ -1 +1 @@
1
- {"mean_reward": -8.83563433215022, "std_reward": 4.761476401782387, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-01-22T10:06:51.493488"}
 
1
+ {"mean_reward": -7.971677318960428, "std_reward": 5.482451777754039, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-01-22T10:17:48.797950"}
vec_normalize.pkl CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:01934633fdbed1f12c3c3b3b46f2194c8a8cf886b9301c3146bbad068cc83816
3
  size 3536
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3ed3bf619481e1e6a99d1030f5a7c7846bf96fc61e08e826aa362116f9c3d377
3
  size 3536