Initial commit

README.md

@@ -16,7 +16,7 @@ model-index:
       type: PandaReachDense-v3
     metrics:
     - type: mean_reward
-      value: -0.19 +/- 0.11
+      value: -0.20 +/- 0.10
       name: mean_reward
       verified: false
 ---

a2c-PandaReachDense-v3.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1f235702b1b97e62bd05c64ef4f851aabec6081f4989ef0471920421c19466e1
+oid sha256:ddada2454d5628bceb538ef32aeb3b7a7328ca3aeee16273ddf0740edbf8f2e7
 size 110330

results.json

@@ -1 +1 @@
-{"mean_reward": -0.19389866702258587, "std_reward": 0.10520347085859763, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-11-26T08:52:09.612623"}
+{"mean_reward": -0.19787778854370117, "std_reward": 0.09500995275534672, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-11-26T08:56:13.239971"}

vec_normalize.pkl

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6ae046898f798943d2c4c086733916efaf0ce551fc3d4827a12ee99a0a702e83
+oid sha256:5a2f066f25d6d5ab8d69a8ec7daf229e6919d78726be3c035cb306ae200b8787
 size 2652