PPO-LunarLander-v2 / results.json
Ryandry1st's picture
Initial model for DRL with HF lesson 1 results
ad1b69c
{"mean_reward": 282.4192603504858, "std_reward": 16.853766422760234, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-01-12T15:33:56.828198"}