Initial commit

README.md

@@ -16,7 +16,7 @@ model-index:
       type: PandaReachDense-v3
     metrics:
     - type: mean_reward
-      value: -0.24 +/- 0.12
+      value: -0.18 +/- 0.08
       name: mean_reward
       verified: false
 ---

a2c-PandaReachDense-v3.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:25ea0d47a63a42233adb94dc159d37b68def823623a0989480587f5b405e2d6d
+oid sha256:d3d3cb81d7616ff2e3bfbc1b9fc777172cb1e884350bea1a9a1ee0b7b736f116
 size 113893

results.json

@@ -1 +1 @@
-{"mean_reward": -0.23531257566064595, "std_reward": 0.11941400177193005, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-11-30T14:21:29.881054"}
+{"mean_reward": -0.18377328384667635, "std_reward": 0.08018128116977373, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-11-30T14:22:33.832019"}

vec_normalize.pkl

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c60a31b625970e07697af72cb72ae1af6560082f55abf12d5c0a494c9e2a723b
+oid sha256:84ace495f36a726c889a1050a1b6f305d62cc23eaddbc8c1b89caee22741a085
 size 2656