Reinforcement Learning and Reactive Search: an adaptive MAX-SAT solver

Abstract

This paper investigates Reinforcement Learning (RL) applied to online parameter tuning in Stochastic Local Search (SLS) methods. In particular, a novel application of RL is proposed in the Reactive Tabu Search (RTS) scheme, where the appropriate amount of diversification in prohibition-based local search is adapted in a fast online manner to the… (More)
DOI: 10.3233/978-1-58603-891-5-909

Topics

2 Figures and Tables

Cite this paper

@inproceedings{Battiti2008ReinforcementLA, title={Reinforcement Learning and Reactive Search: an adaptive MAX-SAT solver}, author={Roberto Battiti and Paolo Campigotto}, booktitle={ECAI}, year={2008} }