Initial commit

README.md

@@ -16,7 +16,7 @@ model-index:
       type: PandaReachDense-v3
     metrics:
     - type: mean_reward
-      value: -0.24 +/- 0.08
+      value: -0.20 +/- 0.07
       name: mean_reward
       verified: false
 ---

a2c-PandaReachDense-v3.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:205449004c0167eccf3e67963b2e491d8ed9a83a36d36066973ddf1de6884796
+oid sha256:41710b0830d6690a0514bcc70e3dfb34834dffcda3768a2d0bead47a67dfadfa
 size 113801

results.json

@@ -1 +1 @@
-{"mean_reward": -0.23589024180546403, "std_reward": 0.07959462414083276, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2025-02-22T18:12:58.070373"}
+{"mean_reward": -0.19669635985046624, "std_reward": 0.07068816308031849, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2025-02-22T18:27:35.281468"}

vec_normalize.pkl

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ca71497a9fabc291edef2b20882e35d8e16bfe7c71e76682aea741d8381e5a02
-size 2643
+oid sha256:6e3398496b8eac1c13409e3ee1b869ec48124f9c3f8d29211d9ab2a32890b926
+size 2656