Initial commit

README.md

@@ -16,7 +16,7 @@ model-index:
       type: PandaReachDense-v2
     metrics:
     - type: mean_reward
-      value: -2.79 +/- 0.83
+      value: -3.04 +/- 1.11
       name: mean_reward
       verified: false
 ---

a2c-PandaReachDense-v2.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2af5d93730839c0b43cb67d56e236b10d88f86a1282b2ed48400f3652514f452
+oid sha256:1680f1545926d3cfd9eb453858c1c21a9b9c3a911ce37534a8afc5798d6fc7fd
 size 108159

results.json

@@ -1 +1 @@
-{"mean_reward": -2.7863451753742994, "std_reward": 0.8282814435093521, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-04-30T10:08:44.277356"}
+{"mean_reward": -3.0440228168852626, "std_reward": 1.1120917680675264, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-04-30T11:45:15.785791"}

vec_normalize.pkl

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8b3a532045636f5b4092c5784a14f229c7981c7fb46c706fbf4aeb1f71e4bb7b
+oid sha256:73811e3614e8e3a4782c99ca348b5e2587435d058def8d629572d41b913efb9b
 size 2387