Initial commit

README.md

@@ -16,7 +16,7 @@ model-index:
       type: PandaReachDense-v2
     metrics:
     - type: mean_reward
-      value: -4.58 +/- 0.93
+      value: -4.20 +/- 1.12
       name: mean_reward
       verified: false
 ---

a2c-PandaReachDense-v2.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e13b9b8804a9a615745d752328fc1e51a10eef2bd238bb71fa0129b0bc3b0db0
+oid sha256:5cbf8c18c0cd26085c26cc16b3b879dcb691491be790da901d2040f47bd319b6
 size 108075

results.json

@@ -1 +1 @@
-{"mean_reward": -4.578705243393779, "std_reward": 0.9333621828090983, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-05-26T21:18:11.086938"}
+{"mean_reward": -4.200978013593703, "std_reward": 1.116948202964026, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-05-26T21:22:17.073396"}

vec_normalize.pkl

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b8709daca8c78c660f2ddd7ebecde56f17db428560d3c9dc193394f1d3775444
+oid sha256:624f306df5183013dd962a02a687692ee2be3de49842d7261980e536b5276ba1
 size 2387