Learning heuristic policies – a reinforcement learning problem

Authors:
Thomas Philip Runarsson
Affiliations:
School of Engineering and Natural Sciences, University of Iceland, Iceland
Venue:
LION'05 Proceedings of the 5th international conference on Learning and Intelligent Optimization
Year:
2011

Citing 8
Cited 0

Introduction to Reinforcement Learning

Introduction to Reinforcement Learning
A Study of Some Properties of Ant-Q

PPSN IV Proceedings of the 4th International Conference on Parallel Problem Solving from Nature
Choosing search heuristics by non-stationary reinforcement learning

Metaheuristics
Approximate Dynamic Programming: Solving the Curses of Dimensionality (Wiley Series in Probability and Statistics)

Approximate Dynamic Programming: Solving the Curses of Dimensionality (Wiley Series in Probability and Statistics)
A reinforcement learning approach to job-shop scheduling

IJCAI'95 Proceedings of the 14th international joint conference on Artificial intelligence - Volume 2
Coalition-based metaheuristic: a self-adaptive metaheuristic using reinforcement learning and mimetism

Journal of Heuristics
A genetic programming hyper-heuristic approach for evolving 2-D strip packing heuristics

IEEE Transactions on Evolutionary Computation
Ant colony system: a cooperative learning approach to the traveling salesman problem

IEEE Transactions on Evolutionary Computation

Quantified Score

Hi-index	0.00

Visualization

Abstract

How learning heuristic policies may be formulated as a reinforcement learning problem is discussed. Reinforcement learning algorithms are commonly centred around estimating value functions. Here a value function represents the average performance of the learned heuristic algorithm over a problem domain. Heuristics correspond to actions and states to solution instances. The problem of bin packing is used to illustrate the key concepts. Experimental studies show that the reinforcement learning approach is compatible with the current techniques used for learning heuristics. The framework opens up further possibilities for learning heuristics by exploring the numerous techniques available in the reinforcement learning literature.