deep-rl-course / results.json
sigma-bit-dot's picture
train ppo model with 1,000,000 time steps
6f66be1
{"mean_reward": 215.0883739, "std_reward": 79.88212942634392, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-12-11T23:17:08.579406"}