Initial commit

README.md

@@ -16,7 +16,7 @@ model-index:
       type: PandaReachDense-v3
     metrics:
     - type: mean_reward
-      value: -0.18 +/- 0.13
+      value: -0.20 +/- 0.09
       name: mean_reward
       verified: false
 ---

a2c-PandaReachDense-v3.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c4b0dc9885d57e27e66bbf08d68c1550b75efcb97486b4368f8ad613cadf990d
+oid sha256:b7df87ce5a8dee17d40297ff26068c74f111f7df65af83f70fef996ff64d1e7d
 size 106976

results.json

@@ -1 +1 @@
-{"mean_reward": -0.1798908685334027, "std_reward": 0.13141850938212118, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-09-08T21:28:58.490274"}
+{"mean_reward": -0.19528527054935693, "std_reward": 0.08861739202311851, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-09-08T21:46:21.009637"}

vec_normalize.pkl

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2e5d5e8bbbfe0ce9c424835d246b61bcbaa8a7296f0b8076a9d8c935e8ac5084
-size 2636
+oid sha256:20a9241ff290a95cae8228fb6e93633e677b3e2f8884086e1afa0ccee4af7fc5
+size 2623