pages 1836--1844, 2014
Williamstown, Masachusetts, U
International In Games18th Proc
Q-Learning Friend-or-Foe MLLittman
31st The maximization
distance Wang HNie FRobust HHuang
Robust and Effective Metric Learning Using Capped Trace Norm
Utility Based Q-learning to Maintain Cooperation in Prisoner’s Dilemma Games