Upload PPO LunarLander-v2 trained agent

README.md

@@ -10,7 +10,7 @@ model-index:
   results:
   - metrics:
     - type: mean_reward
-      value: 294.60 +/- 19.92
+      value: 286.86 +/- 16.85
       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:be8bee32da08c070ad5d3092e3f87b666d0b1ae510aa6404ccf8bdb274652903
+oid sha256:336627851cfd2f71f7235bd3f9cadeaf705fd9b1cd262e4e3029fe94f1c31cfb
 size 145900

replay.mp4

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d132435bfdf11164317442226c5d08b9127aad959538846c3f6d5a9d23045fbd
-size 195459
+oid sha256:215e64dfd77cfaa99509dd025c497d734c3b4d0d06f4b81fdc97e65bc272cc86
+size 195001

results.json

@@ -1 +1 @@
-{"mean_reward": 294.6001049229093, "std_reward": 19.920547442049582, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-05-11T16:47:12.615957"}
+{"mean_reward": 286.86356225425817, "std_reward": 16.851408597981305, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-05-11T16:48:30.864872"}