My first commit to ykirpichev/PPO-LunarLander-v2

README.md

@@ -10,7 +10,7 @@ model-index:
   results:
   - metrics:
     - type: mean_reward
-      value: 263.21 +/- 17.13
+      value: 264.20 +/- 15.99
       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:f1c03514770614fd5c1b0bfecae6def8efabbad36d6d25e72a232d4562ef9307
+oid sha256:18e54e1063bb638ce051b7dac9c55495e9632d2aa10d6e49b1d07fc53e0d8e01
 size 144074

replay.mp4

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6e8d93c7955a01acff8da04d036dc19437618737877853bff1a5d3e9c03e3480
-size 244250
+oid sha256:b62d83c6484f87fd33245d64323f7deef70ced5e16125332009750a41a588504
+size 248339

results.json

@@ -1 +1 @@
-{"mean_reward": 263.21327556857295, "std_reward": 17.133974017497433, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-05-07T18:32:08.660798"}
+{"mean_reward": 264.1974317215029, "std_reward": 15.99019806437835, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-05-07T18:43:55.308924"}