Initial commit

README.md

@@ -16,7 +16,7 @@ model-index:
       type: PandaReachDense-v3
     metrics:
     - type: mean_reward
-      value: -0.18 +/- 0.07
+      value: -0.24 +/- 0.13
       name: mean_reward
       verified: false
 ---

a2c-PandaReachDense-v3.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:18d190bd7d6287690c1d31a59b581d1fb296bc713fe57cd33f2ec4e20cc0aa93
+oid sha256:fdab735b64dea959e002266497aca6034f2c4105b81bcbc20e7a83d7d7d07156
 size 113567

results.json

@@ -1 +1 @@
-{"mean_reward": -0.17992141926661134, "std_reward": 0.0674233667198652, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-11-17T17:06:10.196681"}
+{"mean_reward": -0.23560139266774058, "std_reward": 0.1348832904828822, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-11-17T17:07:59.292221"}

vec_normalize.pkl

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:adb265c216aed6d8ff6d3335d8fda0906535dc5972e30bd12e77261066ba5254
-size 2646
+oid sha256:342993ee95a07b868cd6c8bc613b4a108ad67b5a50436b1c188593fa30e08065
+size 2659