Upload PPO LunarLander-v2 trained agent

README.md

@@ -10,7 +10,7 @@ model-index:
   results:
   - metrics:
     - type: mean_reward
-      value: 293.12 +/- 16.74
+      value: 296.42 +/- 11.35
       name: mean_reward
     task:
       type: reinforcement-learning
@@ -23,3 +23,4 @@ model-index:
 
 
 
+

ppo-LunarLander-v2.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4ab7fb60283cf7049e35220a6e259fffc34abdd2af95193afb115a055630b9a0
+oid sha256:1a8b271078669846083a040af52a2d4bc35910512611f1cd8d6916c63ad50932
 size 143853

replay.mp4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:33aab0ca02a37f10f86ffc62ad95b03c9f4e1fa406c2167c86c18cc344be417a
+size 179052

results.json

@@ -1 +1 @@
-{"mean_reward": 293.11987152138465, "std_reward": 16.73889138903816, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-05-11T17:12:07.385787"}
+{"mean_reward": 296.4151299183745, "std_reward": 11.34848650358931, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-05-11T17:15:02.137367"}