Initial commit

README.md

@@ -16,7 +16,7 @@ model-index:
       type: PandaReachDense-v3
     metrics:
     - type: mean_reward
-      value: -0.26 +/- 0.08
+      value: -0.24 +/- 0.07
       name: mean_reward
       verified: false
 ---

a2c-PandaReachDense-v3.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f37bd7f3235030a7853381f684dce2a5d7a2aabe4343141807145cb53ec4067d
+oid sha256:dd8da865975e1d1e1787ce283ea30d2a0889d8433ac5cdb7beb8a58573305cd9
 size 110246

results.json

@@ -1 +1 @@
-{"mean_reward": -0.2553078759461641, "std_reward": 0.08252185681190607, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-11-19T11:44:22.445474"}
+{"mean_reward": -0.24159235861152412, "std_reward": 0.07259060524668308, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-11-19T11:47:27.421708"}

vec_normalize.pkl

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:112eb7735dc8c30684addf5089574f8fe8bf79d186c102d6fb1bf84d4db5c4c1
+oid sha256:bb202e958736f11f3d03af87dcdc8f27e0c30c26c3363aa3432b8f7966654b09
 size 2659