Initial commit

README.md

@@ -16,7 +16,7 @@ model-index:
       type: PandaReachDense-v3
     metrics:
     - type: mean_reward
-      value: -0.25 +/- 0.06
+      value: -0.27 +/- 0.10
       name: mean_reward
       verified: false
 ---

a2c-PandaReachDense-v3.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:983059c45143aa3c50b111d376942094bdc64258f4243467d977bcb76983e935
+oid sha256:a495b3fe9b7f42151f290390edacaa80dcf871339beacf6c6ab01a85d39a0759
 size 110344

results.json

@@ -1 +1 @@
-{"mean_reward": -0.24866956025362014, "std_reward": 0.06204363759922522, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-02-11T12:04:06.009292"}
+{"mean_reward": -0.2698256950825453, "std_reward": 0.10193835509721559, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-02-11T12:05:12.549516"}

vec_normalize.pkl

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9e73d1d5716b7caace01490768c5f053ec0324061cdfebe44be42345b489d67f
+oid sha256:4c022f9d6ffe60350262a18cf3a4a9cdfd28e4f49332a423fbd49a45cf324795
 size 2659