PAC Reinforcement Learning Algorithm for General-Sum Markov Games

no code implementations • 5 Sep 2020 • Ashkan Zehfroosh, Herbert G. Tanner

This paper presents a theoretical framework for probably approximately correct (PAC) multi-agent reinforcement learning (MARL) algorithms for Markov games.

Multi-agent Reinforcement Learning Q-Learning +2

A Hybrid PAC Reinforcement Learning Algorithm

no code implementations • 5 Sep 2020 • Ashkan Zehfroosh, Herbert G. Tanner

This paper offers a new hybrid probably approximately correct (PAC) reinforcement learning (RL) algorithm for Markov decision processes (MDPs) that intelligently maintains favorable features of its parents.

Q-Learning reinforcement-learning +1