RL Agent for Lunar lander. n_epochs = 4,

gamma = 0.999,
gae_lambda = 0.98,
ent_coef = 0.01,

README.md

@@ -16,7 +16,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: 260.04 +/- 22.33
+      value: 245.48 +/- 48.97
       name: mean_reward
       verified: false
 ---

ppo-LunarLander-v2.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:42694d113b5477445f3a3d8b8d2591d629f7c6ef97483f6801c99f83322e1869
+oid sha256:fa958c26f6c2fce45666788abb5af3b28db853a4716fa12bd3caf04c83926386
 size 147114

results.json

@@ -1 +1 @@
-{"mean_reward": 260.03889289999995, "std_reward": 22.332375751897892, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-06-28T19:25:40.145175"}
+{"mean_reward": 245.48345319999999, "std_reward": 48.96692767228334, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-06-28T19:28:28.226237"}