Initial commit

README.md

@@ -16,7 +16,7 @@ model-index:
       type: PandaReachDense-v3
     metrics:
     - type: mean_reward
-      value: -0.23 +/- 0.09
+      value: -0.21 +/- 0.11
       name: mean_reward
       verified: false
 ---

a2c-PandaReachDense-v3.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d6c708f0b1b0bf92e7d896bc458a5bece5c599c3f1e5c86ba212784b45ac930e
+oid sha256:7f525647e5c50d25eace048d6330a4840d739ff001253d4f9c9276ec11bc096f
 size 110330

results.json

@@ -1 +1 @@
-{"mean_reward": -0.2322616652760189, "std_reward": 0.09463578452712583, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-11-26T17:14:41.148107"}
+{"mean_reward": -0.21168823838233947, "std_reward": 0.11491358954927111, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-11-26T17:18:44.686730"}

vec_normalize.pkl

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5311008a24dfe4710f9a3dc21184117d81b4ea8db63755a050fbc6b5a6ab10fe
-size 2646
+oid sha256:1cf46bdb74bb08b346cc2c75f51e480644f2a559a53f79c5770597e950e8a553
+size 2659