Initial commit

README.md

@@ -16,7 +16,7 @@ model-index:
       type: PandaReachDense-v2
     metrics:
     - type: mean_reward
-      value: -2.23 +/- 1.47
+      value: -2.06 +/- 0.98
       name: mean_reward
       verified: false
 ---

a2c-PandaReachDense-v2.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ae2254dea689f01977cab2cf49083be71079ea5a2e6002b30d55bb4934c3e27a
+oid sha256:3ecd6c54310cf068268f2b2b43910a603d94bc75823627af562e31839508313e
 size 108075

results.json

@@ -1 +1 @@
-{"mean_reward": -2.23145206652116, "std_reward": 1.4718677122110162, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-05-30T06:37:10.070316"}
+{"mean_reward": -2.0564943390432746, "std_reward": 0.9808329492027861, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-05-30T06:45:45.561782"}

vec_normalize.pkl

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:45a0850ed96da8776410fae291afee9fa5842fe25d4019f23d1717a709a11a45
+oid sha256:49a6981fafbfafa944874c97fa3db0218ffb654d7d765a60c09d082626fe5571
 size 2387