Initial commit

README.md

@@ -16,7 +16,7 @@ model-index:
       type: PandaReachDense-v3
     metrics:
     - type: mean_reward
-      value: -0.18 +/- 0.12
+      value: -0.27 +/- 0.14
       name: mean_reward
       verified: false
 ---

a2c-PandaReachDense-v3.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:60465dc6d26c00aa62328ac14be2ee11116dcb4593c89d5a48b1bacf33b3ea94
+oid sha256:bd7e153b480aba23c5c43e2ff58e51d6bd676263cb2a30270882a0eb7db642b9
 size 114041

results.json

@@ -1 +1 @@
-{"mean_reward": -0.18455779030919076, "std_reward": 0.11585565852733218, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-11-17T23:32:02.276401"}
+{"mean_reward": -0.26798432506620884, "std_reward": 0.14424200496237008, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-11-17T23:34:01.963187"}

vec_normalize.pkl

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6c0f7778edc14c5591dd6ec67070d1679396ae84faa5bbd34949f8e0db35bcf0
-size 2646
+oid sha256:10192ddfa9f8de2e01e746f954aed3143e532bd890ec9930bd6fa231b792aad2
+size 2659