Initial commit

README.md

@@ -16,7 +16,7 @@ model-index:
       type: PandaReachDense-v3
     metrics:
     - type: mean_reward
-      value: -0.20 +/- 0.12
+      value: -0.31 +/- 0.15
       name: mean_reward
       verified: false
 ---

a2c-PandaReachDense-v3.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f5cb747688ebad6f85cdc61a588b5af0d06cfddaeb6dfab4e6fef539ba62ab68
+oid sha256:625652f509d65f6b7a790b34d2d69be9e28e11255ff4dbe08544a28457c79329
 size 110260

results.json

@@ -1 +1 @@
-{"mean_reward": -0.20056756753474475, "std_reward": 0.1172141748762625, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-12-18T22:23:41.848157"}
+{"mean_reward": -0.3121505519375205, "std_reward": 0.15034626580840485, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-12-18T22:24:01.809833"}

vec_normalize.pkl

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a3c49372f6e9bfeb107cb9f10aa9b86c8fa1bab87307ed2616de22059af65c20
-size 2646
+oid sha256:ce9074502e9acc7caaa21ec9dd4c48be2201d5b7fcc3c34229f95a8973bd0bdc
+size 2659