Initial commit

README.md

@@ -16,7 +16,7 @@ model-index:
       type: PandaReachDense-v3
     metrics:
     - type: mean_reward
-      value: -0.18 +/- 0.10
+      value: -0.19 +/- 0.11
       name: mean_reward
       verified: false
 ---

a2c-PandaReachDense-v3.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a2d887f604897947ad0656ce83bb451769d81ad9d1d439ce26924154f2110fe8
+oid sha256:f74e418656b9781b64a49ba32fccd39010b48dea767cdd4477d59f51c3e6bb3a
 size 115053

results.json

@@ -1 +1 @@
-{"mean_reward": -0.17631225464865566, "std_reward": 0.10029821388698813, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2025-07-22T14:49:55.026208"}
+{"mean_reward": -0.18583574034273626, "std_reward": 0.10747055766168512, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2025-07-22T14:51:43.413213"}

vec_normalize.pkl

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:638363fc615bb167f917e1682c9d8712f33ff048d902d02ce9032a1eb1c35ca4
+oid sha256:2ed9ceb6430ec1a1b7a03e939ba361116078709cbd2788a2751e8512169d346c
 size 2657