PPO-LunarLander-v2 / results.json
shivr's picture
Initial PPO model on 1000000 training steps
ad41807
{"mean_reward": 248.36929905686097, "std_reward": 18.67775658437734, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-05-24T00:31:01.347427"}