|
Solving Multi-Stage Games with Hierarchical Learning Automata that Bootstrap Host Publication: Adaptive Agents and Multi-Agent Systems III. Adaptation and Multi-Agent Learning Authors: M. Peeters, K. Verbeeck and A. Nowé Publisher: Springer Publication Date: Feb. 2008 ISBN: 978-3-540-77947-6
Abstract: Hierarchical learning automata are shown to be an excellent
tool for solving multi-stage games. However, most updating schemes used
by hierarchical automata expect the multi-stage game to reach an ab-
sorbing state at which point the automata are updated in a Monte Carlo
way. As such, the approach is infeasible for large multi-stage games (and
even for problems with an infinite horizon) and the convergence process
is slow. In this paper we propose an algorithm where the rewards do not
have to travel all the way up to the top of the hierarchy and in which
there is no need for explicit end-stages.
|
