Jarlaxle
My best trained agent for LunarLander-v2 task. I selected learning rate, gamma, gae_lambda and entropy through optuna.
e04d742
{"mean_reward": 291.6055645, "std_reward": 11.895946395293588, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-12-10T15:22:19.718001"}