Tuning Local Search by Average-Reward Reinforcement Learning

Authors:
Steven Prestwich
Affiliations:
Cork Constraint Computation Centre Department of Computer Science, University College, Cork, Ireland
Venue:
Learning and Intelligent Optimization
Year:
2008

Citing 14
Cited 0

Noise strategies for improving local search

AAAI '94 Proceedings of the twelfth national conference on Artificial intelligence (vol. 1)
Temporal difference learning and TD-Gammon

Communications of the ACM
Average reward reinforcement learning: foundations, algorithms, and empirical results

Machine Learning - Special issue on reinforcement learning
Learning evaluation functions for global optimization and Boolean satisfiability

AAAI '98/IAAI '98 Proceedings of the fifteenth national/tenth conference on Artificial intelligence/Innovative applications of artificial intelligence
Learning instance-independent value functions to enhance local search

Proceedings of the 1998 conference on Advances in neural information processing systems II
Introduction to Reinforcement Learning

Introduction to Reinforcement Learning
Algorithm Selection using Reinforcement Learning

ICML '00 Proceedings of the Seventeenth International Conference on Machine Learning
Choosing search heuristics by non-stationary reinforcement learning

Metaheuristics
Stochastic Local Search: Foundations & Applications

Stochastic Local Search: Foundations & Applications
An empirical analysis of search in GSAT

Journal of Artificial Intelligence Research
A reinforcement learning approach to job-shop scheduling

IJCAI'95 Proceedings of the 14th international joint conference on Artificial intelligence - Volume 2
Scaling and probabilistic smoothing: dynamic local search for unweighted MAX-SAT

AI'03 Proceedings of the 16th Canadian society for computational studies of intelligence conference on Advances in artificial intelligence
Evidence for invariants in local search

AAAI'97/IAAI'97 Proceedings of the fourteenth national conference on artificial intelligence and ninth conference on Innovative applications of artificial intelligence
Random walk with continuously smoothed variable weights

SAT'05 Proceedings of the 8th international conference on Theory and Applications of Satisfiability Testing

Quantified Score

Hi-index	0.00

Visualization

Abstract

Reinforcement Learning and local search have been combined in a variety of ways, in order to learn how to solve combinatorial problems more efficiently. Most approaches optimise the total reward, where the reward at each action is the change in objective function. We argue that it is more appropriate to optimise the average reward. We use R-learning to dynamically tune noise in standard SAT local search algorithms on single instances. Experiments show that noise can be successfully automated in this way.