Comparison between trained DDPG, DWA, and PPO algorithms

Описание к видео Comparison between trained DDPG, DWA, and PPO algorithms

Video comparing the performances in the testing environment of DDPG (after 6000 episodes of training), PPO (after 5000 episodes of training), and the Turtlebot3 Navigation package (DWA).

Комментарии

Информация по комментариям в разработке