Selection and Reinforcement Learning for Combinatorial Optimization

Authors:
Arnaud Berny
Affiliations:
-
Venue:
PPSN VI Proceedings of the 6th International Conference on Parallel Problem Solving from Nature
Year:
2000

Citing 5
Cited 1

Learning automata: an introduction

Learning automata: an introduction
Simple Statistical Gradient-Following Algorithms for Connectionist Reinforcement Learning

Machine Learning
Using expectation-maximization for reinforcement learning

Neural Computation
Statistical machine learning and combinatorial optimization

Theoretical aspects of evolutionary computing
The equation for response to selection and its use for prediction

Evolutionary Computation

Extending Selection Learning toward Fixed-Length d-Ary Strings

Selected Papers from the 5th European Conference on Artificial Evolution

Quantified Score

Hi-index	0.00

Visualization

Abstract

Improving on a previous paper, we explicitly relate reinforcement and selection learning (PBIL) algorithms for combinatorial optimization, which is understood as the task of finding a fixed-length binary string maximizing an arbitrary function. We show the equivalence of searching for an optimal string and searching for a probability distribution over strings maximizing the function expectation. In this paper however, we will only consider the family of Bernoulli distributions. Next, we introduce two gradient dynamical systems acting on probability vectors. The first one maximizes the expectation of the function and leads to reinforcement learning algorithms whereas the second one maximizes the logarithm of the expectation of the function and leads to selection learning algorithms. We finally give a stability analysis of solutions.