Upload PPO BipedalWalker-v3 trained agent

README.md

@@ -16,7 +16,7 @@ model-index:
       type: BipedalWalker-v3
     metrics:
     - type: mean_reward
-      value: 140.70 +/- 151.23
+      value: 211.89 +/- 132.27
       name: mean_reward
       verified: false
 ---

ppo_walker.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:60f790bec2d7becb3ff60e42a715cbb2269395a4b849ccab13f45035637fbe2a
+oid sha256:d1b0caab33b7163dea93924070a01cf627c857c8698cbb9ad12c2018cd20eeb2
 size 177295

results.json

@@ -1 +1 @@
-{"mean_reward": 140.69508294530567, "std_reward": 151.22843357804928, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-12-10T06:15:41.971787"}
+{"mean_reward": 211.88950655391199, "std_reward": 132.26573792682655, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-12-10T06:22:04.565192"}