Off-Policy Model-Free Learning for Multi-Player Non-Zero-Sum Games With Constrained Inputs
Sign Up to like & getrecommendations! Published in 2023 at "IEEE Transactions on Circuits and Systems I: Regular Papers"
DOI: 10.1109/tcsi.2022.3221274
Abstract: In this paper, multi-player non-zero-sum games with control constraints are studied by utilizing a novel model-free approach based on adaptive dynamic programming framework. First, the model-based policy iteration (PI) method is provided, which requires the… read more here.
Keywords: model free; player non; policy; model ... See more keywords