LunarLander-v2 / results.json
bvk1ng's picture
Adding::Higher timesteps trained PPO based agent
f00c817
raw
history blame contribute delete
163 Bytes
{"mean_reward": 290.8752914142443, "std_reward": 17.27576260261546, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-12-09T17:03:19.731271"}