Approximation of Discounted Minimax Markov Control Problems and Zero-Sum Markov Games Using Hausdorff and Wasserstein Distances
Sign Up to like & getrecommendations! Published in 2019 at "Dynamic Games and Applications"
DOI: 10.1007/s13235-018-0253-y
Abstract: This paper is concerned with a minimax control problem (also known as a robust Markov decision process (MDP) or a game against nature) with general state and action spaces under the discounted cost optimality criterion.… read more here.
Keywords: discounted minimax; approximation; control; sum markov ... See more keywords
Convergence of Decentralized Actor-Critic Algorithm in General–Sum Markov Games
Sign Up to like & getrecommendations! Published in 2024 at "IEEE Control Systems Letters"
DOI: 10.1109/lcsys.2024.3510193
Abstract: Markov games provide a powerful framework for modeling strategic multi-agent interactions in dynamic environments. Traditionally, convergence properties of decentralized learning algorithms in these settings have been established only for special cases, such as Markov zero-sum… read more here.
Keywords: general sum; markov; markov games; actor critic ... See more keywords