Initial commit

README.md

@@ -16,7 +16,7 @@ model-index:
       type: PandaReachDense-v2
     metrics:
     - type: mean_reward
-      value: -5.47 +/- 1.04
+      value: -5.30 +/- 1.77
       name: mean_reward
       verified: false
 ---

a2c-PandaReachDense-v2.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d69e9d91a8ac615adbeb115ff5477ec20e1c65ce1dc4dfaec334656a72dc7b88
+oid sha256:8886628162d84ebdb6c40d0cb7e93ff043c808e02dbddf24def4c3e1d0b27ea5
 size 108023

results.json

@@ -1 +1 @@
-{"mean_reward": -5.472592221386731, "std_reward": 1.0386742933655355, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-04-22T02:50:30.812529"}
+{"mean_reward": -5.299031317140907, "std_reward": 1.7738979616266832, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-04-22T02:58:42.911271"}

vec_normalize.pkl

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:295ba5e55d389bc354f477a3260274a52385192c1f662801ed09c725f3f1c793
+oid sha256:07eeabe77ed7cb38b19ecbb4f0d3ef3347ed6476c0fff3f5685afbf2d08b0724
 size 2381