Upload PPO LunarLander-v2 trained agent

README.md

@@ -10,7 +10,7 @@ model-index:
   results:
   - metrics:
     - type: mean_reward
-      value: 174.31 +/- 19.84
+      value: 132.22 +/- 79.95
       name: mean_reward
     task:
       type: reinforcement-learning

replay.mp4

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fb17b53f56b900641ecd483dee976cf16958217a763b58d4f6d710e10c438eef
-size 249785
+oid sha256:26609226c15c912a850470ae1df7175b6788d83a20f86cc70a31fa813c71725c
+size 249392

results.json

@@ -1 +1 @@
-{"mean_reward": 174.31029362337796, "std_reward": 19.84344226003817, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-05-08T20:13:02.742111"}
+{"mean_reward": 132.22170390692787, "std_reward": 79.94749096612446, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-05-08T20:21:33.120886"}

sendit.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9e1e120cb12cae9efa0a7b4a7fde15f75d15209ef7d480feb30adbd61ba12c26
+oid sha256:c2e27d9311fff66a6318a8e56ee993467a7e1433b14dfdb2317972a9b3da9285
 size 144048