lunar_landerv2_ppo / results.json
advaitadasein's picture
trained mlp agent with ppo algorithm
73eb454
raw
history blame contribute delete
156 Bytes
{"mean_reward": 222.8209238, "std_reward": 73.9527219100079, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-10-12T12:22:26.653974"}