Initial commit

README.md

@@ -16,7 +16,7 @@ model-index:
       type: PandaReachDense-v3
     metrics:
     - type: mean_reward
-      value: -0.88 +/- 1.70
+      value: -0.85 +/- 1.73
       name: mean_reward
       verified: false
 ---

a2c-PandaReachDense-v3.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:90edb930fce0a5d29bced285263b6a908276f8a48743c908a5aaeee64f4cd00b
+oid sha256:58b9fd4decb39fcd9578c212c5ae1c526e1c086885a3efb8dbd6c575a97c76cb
 size 114064

results.json

@@ -1 +1 @@
-{"mean_reward": -0.8803985923528671, "std_reward": 1.6951808741029122, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2025-02-19T11:06:10.519713"}
+{"mean_reward": -0.854161989223212, "std_reward": 1.7320323225487615, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2025-02-19T11:07:22.709499"}

vec_normalize.pkl

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e01a3e31f974b78446fdd770af551629691ab00ffe70b0a9c1567875a05d59d5
-size 2643
+oid sha256:a624e2afa947cb8af2d406bb10ad0bbed031bfde6f9af962917186b4e5d45de2
+size 2656