Initial commit

README.md

@@ -16,7 +16,7 @@ model-index:
       type: PandaReachDense-v3
     metrics:
     - type: mean_reward
-      value: -21.84 +/- 7.46
+      value: -19.86 +/- 7.47
       name: mean_reward
       verified: false
 ---

a2c-PandaReachDense-v3.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:804bb627c283a3d1aaad9910b5d943b9aaaa85d2827fc6a0d193df34368f151d
+oid sha256:fbe2941f8385dd210ec395972e4bf5edf1c5c731dd310f95433e91209fda5c2c
 size 107259

results.json

@@ -1 +1 @@
-{"mean_reward": -21.84275496043265, "std_reward": 7.457779292293829, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-11-06T11:34:22.109625"}
+{"mean_reward": -19.85654140971601, "std_reward": 7.465798216663318, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-11-06T11:48:05.986429"}

vec_normalize.pkl

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8cab4387aaef8b3a1a414a3d1e177ed492ed46cb50e25930e9fb339bfc21626e
+oid sha256:d9733088787eed859072880b75e82aafc9d97dc81fd1122cbe39fc82922edac9
 size 2656