ppo-LunarLander-v2-1m / results.json
dodisbeaver's picture
Upload PPO LunarLander-v2 trained agent 100 000 000 sets
03cc7be
{"mean_reward": 56.071892916987906, "std_reward": 94.28716406069113, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-12-03T20:03:15.308858"}