Initial commit

README.md

@@ -16,7 +16,7 @@ model-index:
       type: PandaReachDense-v3
     metrics:
     - type: mean_reward
-      value: -0.22 +/- 0.11
+      value: -0.16 +/- 0.06
       name: mean_reward
       verified: false
 ---

a2c-PandaReachDense-v3.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b0433711ed5a27a7ee1a0a3fdbbd4b0be0703d4b5369a908ce77bd73b99b771a
+oid sha256:f42ca07aa3f4a3ce2f4933b6a693b001303efe73cc02c6fc1ca0c7cab566c314
 size 114275

results.json

@@ -1 +1 @@
-{"mean_reward": -0.21841081213206054, "std_reward": 0.10890280145003578, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2025-08-14T00:56:01.901590"}
+{"mean_reward": -0.1642621397972107, "std_reward": 0.060019284156923466, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2025-08-14T00:56:22.346439"}

vec_normalize.pkl

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b66fad4750e01c22f5f145ba0e5635b2a62353dc065b371cdaefc234b7a33d2e
+oid sha256:928f65e07f3ccfd72a0775daeeb8af6abb3983247818d5a5ca402b255a9cb1e8
 size 2657