Upload PPO LunarLander-v2 trained for 1M timesteps, mean_reward: 267.19

README.md

@@ -16,7 +16,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: 261.21 +/- 22.08
+      value: 260.54 +/- 20.55
       name: mean_reward
       verified: false
 ---

ppo-LunarLander-v2.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cf8544bc2744a1cbc759db13df6118f15728a18eecc2c866c3727812ddc7ba26
+oid sha256:b631ccd0b0e723355d26fe376d977b5fb7e53a2e29b2be8adc82cce0a21f721c
 size 148132

replay.mp4

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d8839b089521e9567dcd5c854abc0e7da22df8615517fc14743e1ffc0cbe53f8
-size 146330
+oid sha256:209cc4afc586587e2ed699b11f24fe65a41c05b2924d0459a0883e78d988767d
+size 150133

results.json

@@ -1 +1 @@
-{"mean_reward": 261.21285389999997, "std_reward": 22.07892826160764, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2025-08-02T13:51:52.727565"}
+{"mean_reward": 260.5429379941659, "std_reward": 20.54879714526502, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2025-08-02T13:57:20.052892"}