Initial commit

README.md

@@ -16,7 +16,7 @@ model-index:
       type: PandaReachDense-v3
     metrics:
     - type: mean_reward
-      value: -0.17 +/- 0.06
+      value: -0.20 +/- 0.12
       name: mean_reward
       verified: false
 ---

a2c-PandaReachDense-v3.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1ff1f50aee4b681f2271740e1ce7a8b1523cf1577960faf6f6982d8a48082c98
+oid sha256:9a13101dfde54a0fc54956f33016ce83e3628de92cb6e9a6ce913500fe390126
 size 114013

results.json

@@ -1 +1 @@
-{"mean_reward": -0.1700119617395103, "std_reward": 0.06256494538123039, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-11-25T07:22:49.629161"}
+{"mean_reward": -0.19756393171846867, "std_reward": 0.11776633075635323, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-11-25T07:24:36.602585"}

vec_normalize.pkl

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2e42d8ceacfc3f263d6a0764b2fbae9ac7bc8b4a92575bb195bbc648e4768f93
-size 2656
+oid sha256:4cab850ef21a55d4ec39c7d4090a3deb8d1adf366d15ee016bb01badeda6aeab
+size 2643