Initial commit

README.md

@@ -16,7 +16,7 @@ model-index:
       type: PandaReachDense-v3
     metrics:
     - type: mean_reward
-      value: -0.29 +/- 0.12
+      value: -0.15 +/- 0.12
       name: mean_reward
       verified: false
 ---

a2c-PandaReachDense-v3.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d303108f72b9cf28cf4f4415d3c80e98a33df8d61e9fdfc9f7977513a54eeadc
+oid sha256:9cea38eddbb4f4c93102fe97e143295879cd8a17af687ced3a762430ec4ced0c
 size 113914

results.json

@@ -1 +1 @@
-{"mean_reward": -0.28678947761654855, "std_reward": 0.11523175498020068, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2025-04-06T17:35:45.313007"}
+{"mean_reward": -0.15211239419877529, "std_reward": 0.1231624104248271, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2025-04-06T17:38:27.466822"}

vec_normalize.pkl

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1b32db25a5d661eb0ebc88c1fc8676f869bce7b874ba59f551a0b41217aea037
+oid sha256:c325ea1f72c1718170276fef3c5ae3f67d27f0144e94c95ea025f0b6329723ab
 size 2656