Initial commit

README.md

@@ -16,7 +16,7 @@ model-index:
       type: PandaReachDense-v2
     metrics:
     - type: mean_reward
-      value: -6.59 +/- 1.35
+      value: -5.88 +/- 1.67
       name: mean_reward
       verified: false
 ---

a2c-PandaReachDense-v2.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c875c5ef4881dfb1f13864ddaf303b49db5b1bb92e255e7da04c0ae26cf3f991
+oid sha256:ad4f79902b415428e4d700ad15a16d8638917005e7d7673f337e953503bf0c70
 size 107818

replay.mp4

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:49cab7b28cd72648f2be97e3fa677a70b421bff7439574ea53225aa68779fe5f
-size 840445
+oid sha256:f858957c9e3cf56f6d408d3e3f7b06cf81d2f9d70d14f62d745d1d8f40072a83
+size 850720

results.json

@@ -1 +1 @@
-{"mean_reward": -6.588497714884579, "std_reward": 1.3496159602219868, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-07-20T15:23:49.667606"}
+{"mean_reward": -5.875506052421406, "std_reward": 1.667313232263901, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-07-20T15:48:56.753231"}

vec_normalize.pkl

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8fc5ace8f2fdc6638e6d462667796d0348c9748d4d3fa7c2cc79f4495b09b323
+oid sha256:dcbb324f8a9d8860b6d50abfcd2fcd5f2997c0348e8528caa38e12ebb8b10c11
 size 2387