Initial commit

README.md

@@ -16,7 +16,7 @@ model-index:
       type: PandaReachDense-v3
     metrics:
     - type: mean_reward
-      value: -0.23 +/- 0.11
+      value: -0.21 +/- 0.13
       name: mean_reward
       verified: false
 ---

a2c-PandaReachDense-v3.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4065c549e38a6742a932c1bd9b03b15f90efaefa75523450651001f2279008e0
+oid sha256:89943bef70fe8325f85ec5c069f0ebaf9bbeb08a5511e50bcac04dba2973e06d
 size 110260

results.json

@@ -1 +1 @@
-{"mean_reward": -0.23015468437224626, "std_reward": 0.10807186526257202, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-02-12T21:18:04.383426"}
+{"mean_reward": -0.21061385199427604, "std_reward": 0.1264935657036898, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-02-12T21:22:55.790888"}

vec_normalize.pkl

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4c50db6a7024d04e61dd5ee59c4b4c8d437055a2bc0c942120094dc46bd45a08
-size 2646
+oid sha256:0b3e5171d03f7eff15231ea0d99520d0f9b5331b69d627adfabb34c739021e28
+size 2659