Initial commit

README.md

@@ -16,7 +16,7 @@ model-index:
       type: PandaReachDense-v3
     metrics:
     - type: mean_reward
-      value: -0.20 +/- 0.13
+      value: -0.19 +/- 0.12
       name: mean_reward
       verified: false
 ---

a2c-PandaReachDense-v3.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:244e3ee5d3d8f458d8968c7228f99145a945ec129de989845d0a70833182db87
+oid sha256:d2c34c9f70f6c5e35106d488c8ef3094960de78b8b1cc2b2e75a9ddea8cb5729
 size 110260

results.json

@@ -1 +1 @@
-{"mean_reward": -0.19688213597983123, "std_reward": 0.13215131966517044, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-02-06T12:09:02.408773"}
+{"mean_reward": -0.19487485345453023, "std_reward": 0.12076781867535315, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-02-06T12:10:22.052713"}

vec_normalize.pkl

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3f7f095360e2343665031c2e926e74f93a1eecdbb4a38a6ea8f5d6fb40173d53
+oid sha256:65c90b7ef1b0f33485efdcc993cac1c0d22a9d0568b56409e2c2b03531f5eb24
 size 2659