rl_learning / results.json

this is the first test model for lunarlender (10000 steps)

383f2ec verified 8 months ago

166 Bytes

{"mean_reward": -306.40602789999997, "std_reward": 109.48035027781215, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2025-06-03T13:09:14.704765"}