|
The Practical Use of ESRL For Conflicting Interest Games This publication appears in: MICC Technical Report Series Authors: Y. De Hauwere, K. Verbeeck, M. Peeters, A. Nowé and K. Verbeeck Issue: Alamas 2007 Pages: 66-73 Publication Date: Apr. 2007
Abstract: In this paper we tested the practical use of an existing learning algorithm, called Exploring Selfish Reinforcement Learning (ESRL), on conflicting interest games. This algorithm is based on the principles of learning automata and, for games where agents have conflicting interests, on a Homo egualis society. Furthermore we propose some variations on the exploration heuristic of the algorithm and observe how these influence the convergence, fairness and speed results.
|
