pushing first model for the LunarLander-v2 env using PPO with multilayer perceptron architecture
fc9fe9a
| {"mean_reward": 255.02832394306444, "std_reward": 23.3201688344194, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-12-30T14:12:14.598343"} |