Initial commit

README.md

@@ -16,7 +16,7 @@ model-index:
       type: PandaReachDense-v3
     metrics:
     - type: mean_reward
-      value: -0.20 +/- 0.13
+      value: -0.20 +/- 0.10
       name: mean_reward
       verified: false
 ---

a2c-PandaReachDense-v3.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:df804ea810f791d6b95f0abb2f61864dce584d39e11ada54ff87fd9bcc3b454b
+oid sha256:23e9b2e99b041de4eb543e7af3b0a1cdd6a1b373c89d9d1f97a84f2c29a201b0
 size 110260

results.json

@@ -1 +1 @@
-{"mean_reward": -0.19714447651058437, "std_reward": 0.1313899643141471, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-03-04T18:24:41.940277"}
+{"mean_reward": -0.19705171161331236, "std_reward": 0.10036449128954375, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-03-04T18:27:20.839652"}

vec_normalize.pkl

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b168c177abfd789cb00cfc96a3b267bdca60b53f9c82f530ba44fb663913aaaa
+oid sha256:ad86b32fff0fb29274364a3f649f7c1c42866ac53cc5766739f2b24a0f8ff560
 size 2659