Scenario Co-Evolution for Reinforcement Learning on a Grid World Smart Factory Domain

Titelangaben

Gabor, Thomas ; Sedlmeier, Andreas ; Kiermeier, Marie ; Phan, Thomy ; Henrich, Marcel ; Pichlmair, Monika ; Kempter, Bernhard ; Klein, Cornel ; Sauer, Horst ; Schmid, Reiner ; Wieghardt, Jan:
Scenario Co-Evolution for Reinforcement Learning on a Grid World Smart Factory Domain.
In: Proceedings of the Genetic and Evolutionary Computation Conference. - New York, NY, USA : Association for Computing Machinery , 2019 . - S. 898-906 . - (ACM Conferences )
ISBN 978-1-4503-6111-8
DOI: https://doi.org/10.1145/3321707.3321831

Volltext

Link zum Volltext (externe URL):

Angaben zu Projekten

Abstract

Adversarial learning has been established as a successful paradigm in reinforcement learning. We propose a hybrid adversarial learner where a reinforcement learning agent tries to solve a problem while an evolutionary algorithm tries to find problem instances that are hard to solve for the current expertise of the agent, causing the intelligent agent to co-evolve with a set of test instances or scenarios. We apply this setup, called scenario co-evolution, to a simulated smart factory problem that combines task scheduling with navigation of a grid world. We show that the so trained agent outperforms conventional reinforcement learning. We also show that the scenarios evolved this way can provide useful test cases for the evaluation of any (however trained) agent.