Decentralized Q-Learning for Stochastic Teams and Games
Sign Up to like & getrecommendations! Published in 2017 at "IEEE Transactions on Automatic Control"
DOI: 10.1109/tac.2016.2598476
Abstract: There are only a few learning algorithms applicable to stochastic dynamic teams and games which generalize Markov decision processes to decentralized stochastic control problems involving possibly self-interested decision makers. Learning in games is generally difficult… read more here.
Keywords: decision; teams games; decision makers; learning stochastic ... See more keywords
Decentralized Learning for Optimality in Stochastic Dynamic Teams and Games with Local Control and Global State Information
Sign Up to like & getrecommendations! Published in 2021 at "IEEE Transactions on Automatic Control"
DOI: 10.1109/tac.2021.3121228
Abstract: Stochastic dynamic teams and games are rich models for decentralized systems and challenging testing grounds for multi-agent learning. Several algorithms exist for stochastic games, some with guarantees of convergence to equilibrium. However, there may be… read more here.
Keywords: teams games; optimality; global state; control ... See more keywords