Commit a2c-1 model

README.md

@@ -16,7 +16,7 @@ model-index:
       type: PandaReachDense-v3
     metrics:
     - type: mean_reward
-      value: -0.21 +/- 0.09
+      value: -0.24 +/- 0.11
       name: mean_reward
       verified: false
 ---

a2c-1-PandaReachDense-v3.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:25f2e179e85cbed9c50eaec24901bf5bec86c8f1f3248d0d1b233ff5a3d7d25d
+oid sha256:65d4e5062dea13f7479ed5a6a5e7a955b65f78fd136b1a7766622c2e5ae8991e
 size 116078

results.json

@@ -1 +1 @@
-{"mean_reward": -0.2063188442029059, "std_reward": 0.09475101784902458, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-01-05T17:15:04.906917"}
+{"mean_reward": -0.2368618691340089, "std_reward": 0.10845436223118013, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-01-05T17:15:33.895830"}

vec_normalize.pkl

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:576a9fecec2e35cb27aa07b7ea88e7258b98127dc2e6bb4e58bc8698de37ec15
+oid sha256:ab83dbfa696db1ba75075927bc4d63a24bd263b5bd256178112b651d79b53a44
 size 2916