Integral Reinforcement Learning for online computation of feedback Nash strategies of nonzero-sum differential games
Integral Reinforcement Learning for online computation of feedback Nash strategies of nonzero-sum differential games
D. Vrabie,F. Lewis
2010 · DOI: 10.1109/CDC.2010.5718152
IEEE Conference on Decision and Control · 引用数 60
TLDR
An Approximate/Adaptive Dynamic Programming (ADP) algorithm that finds online the Nash equilibrium for two-player nonzero-sum differential games with linear dynamics and infinite horizon quadratic cost is presented.