Uploading nouvelle version PPO Lunar Lander trained agent

README.md

@@ -10,7 +10,7 @@ model-index:
   results:
   - metrics:
     - type: mean_reward
-      value: 230.89 +/- 91.05
+      value: 299.23 +/- 10.04
       name: mean_reward
     task:
       type: reinforcement-learning

ppo-LunarLander-v2.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1026c008ed10bb64d99e41c3d75fdbc973437fbc3fb5b9ab8f09749acee79545
+oid sha256:d09bb6cf97ef40745d73ce36f9fd56ff19313d35980625f09a1ca6e0277d35cb
 size 143989

replay.mp4

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b0254e7b7cd25add9e5e1630f807d1d98d17ce8e9d3462b3e3c58fc2899d0bc9
-size 176052
+oid sha256:d47543938791dbedbf97323c941b26338d453135e7412187fede6ae4ffa46f9e
+size 170219

results.json

@@ -1 +1 @@
-{"mean_reward": 230.88679136796455, "std_reward": 91.05147991059931, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-05-13T22:30:36.977319"}
+{"mean_reward": 299.229638625363, "std_reward": 10.035278721458194, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-05-13T22:33:00.651242"}