Initial commit

README.md

@@ -16,7 +16,7 @@ model-index:
       type: PandaReachDense-v3
     metrics:
     - type: mean_reward
-      value: -0.23 +/- 0.12
+      value: -0.25 +/- 0.18
       name: mean_reward
       verified: false
 ---

a2c-PandaReachDense-v3.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3591e41d612b0894b05af0a2084fc9d7edde557edbeb1bfdc63b6e24683c568b
+oid sha256:0b77bb9887dd63438b5bfdcc3085ba24556655c6e89c8ffbef3d084d493d75dd
 size 110808

results.json

@@ -1 +1 @@
-{"mean_reward": -0.23159173028543592, "std_reward": 0.11520090810125444, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-05-05T11:54:46.160708"}
+{"mean_reward": -0.25074434783309696, "std_reward": 0.17686055257393163, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-05-05T11:58:34.589270"}

vec_normalize.pkl

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:10b73d6f545f90ce9f3d11d08851180caf58e5ec6e28e9ffcd5ad92ad06d0f01
+oid sha256:8acd336f99479e9c7641e2820e13d3820a4f51a0f5b09b51b307ea85a12cba67
 size 2659