Initial commit

README.md

@@ -16,7 +16,7 @@ model-index:
       type: PandaReachDense-v2
     metrics:
     - type: mean_reward
-      value: -2.90 +/- 1.17
+      value: -2.48 +/- 0.68
       name: mean_reward
       verified: false
 ---

a2c-PandaReachDense-v2.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:76260730308ce64b0b6abe03ac8e131d7d0e23a1e9c95b11bb5f2e993ca9424b
+oid sha256:10c6c371fb812979f82988b55ef1d5b9488dbfddf88a30301e26f6b32a091f6a
 size 108095

results.json

@@ -1 +1 @@
-{"mean_reward": -2.9025278366170824, "std_reward": 1.1689517862690673, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-03-01T20:53:15.363276"}
+{"mean_reward": -2.4773715982213615, "std_reward": 0.6783112181642464, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-03-01T20:53:23.586219"}

vec_normalize.pkl

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:10cc69dd30fbaf79871d224e7a4b0deb9f59f76dd681af5cebd69c74cc448999
+oid sha256:c3f8afe58e4e99e21f451d4194db4b1d48e715c118a89bdbde577022259945eb
 size 3056