Value Function and Lyapunov function comparison

preview_player
Показать описание
Comparison between the value function obtained by reinforcement learning to lyanpunov function for an inverted pendulum model.
Рекомендации по теме
Комментарии
Автор

Wow.. So basically, is value function in RL the approximation of Lyapunov function?

flyshanefly
join shbcf.ru