Initial commit

README.md

@@ -16,7 +16,7 @@ model-index:
       type: PandaReachDense-v3
     metrics:
     - type: mean_reward
-      value: -0.21 +/- 0.11
+      value: -0.17 +/- 0.08
       name: mean_reward
       verified: false
 ---

a2c-PandaReachDense-v3.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5cfcf0b54fa6889a4e7377e8c17971ee9518423cf604db455debc9000fc8cd0b
+oid sha256:58ed65e380947e58375500ef71b2aa0b359e9a56abbe9d6e64d5d53b2e538431
 size 113682

results.json

@@ -1 +1 @@
-{"mean_reward": -0.20767162200063466, "std_reward": 0.10946952084723618, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-10-28T10:06:19.402045"}
+{"mean_reward": -0.17406921442598106, "std_reward": 0.0835345455494985, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-10-28T10:10:49.400249"}

vec_normalize.pkl

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7f2a41a5bb3cca0a1558b3d8fd5a3be7f79259a74d3857efae12f72433481d66
-size 2646
+oid sha256:4c62484a21d8b4ff148fb3cb2ce96266feb1bd42b0827e27311dcb1ac12e1dd7
+size 2659