Upload PPO LunarLander-v2 trained agent

README.md

@@ -10,7 +10,7 @@ model-index:
   results:
   - metrics:
     - type: mean_reward
-      value: -204.84 +/- 56.87
+      value: -141.67 +/- 40.61
       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:b56966499411987d4e2159023440e948a7daff012be9277d1ce2da908fc1b55e
-size 188334
+oid sha256:e76864629afd68ae5fed33dbe55790a6a75e12918ae97eeecb573f6807cbaead
+size 188333

ppo-LunarLander-v2/policy.optimizer.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8c485128cd1e6ce0c90039958eaec9c65f14a96806c671564162c469b40f473d
+oid sha256:4b303dba5f95837aabc886446c27ad5b225301d2824e2f3c006c57c00e54988a
 size 84893

ppo-LunarLander-v2/policy.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0a6a337206b25e3116ec836ff7cf30dd91c54db046078f30e5214e07f9ed95d1
+oid sha256:a33c08c82f08f3da19f216c2fe27ff798142b8a7943fdb635ad273b3969dcec8
 size 43201

replay.mp4

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:450b1e58e40bf74297a26580840083fa14167b07a47d9ea2a8e46736f8f44c86
-size 247626
+oid sha256:f852ea287c2cc0a3ccba4ea012b09721530622c1629cd4c86ad79c81a49e63eb
+size 253943

results.json

@@ -1 +1 @@
-{"mean_reward": -204.84463142059175, "std_reward": 56.87323539444302, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-05-05T13:50:21.022000"}
+{"mean_reward": -141.66860129119596, "std_reward": 40.6133855839029, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-05-05T14:16:29.289943"}