Finding hidden hierarchy in reinforcement learning

Authors:
Geoff Poulton;Ying Guo;Wen Lu
Affiliations:
Autonomous Systems, Information and Communication Technology Centre, CSIRO, Epping, Australia;Autonomous Systems, Information and Communication Technology Centre, CSIRO, Epping, Australia;University of NSW, Australia
Venue:
KES'05 Proceedings of the 9th international conference on Knowledge-Based Intelligent Information and Engineering Systems - Volume Part III
Year:
2005

Citing 5
Cited 0

New faster Kernighan-Lin-type graph-partitioning algorithms

ICCAD '93 Proceedings of the 1993 IEEE/ACM international conference on Computer-aided design
Introduction to Reinforcement Learning

Introduction to Reinforcement Learning
Discovering Hierarchy in Reinforcement Learning with HEXQ

ICML '02 Proceedings of the Nineteenth International Conference on Machine Learning
Feudal Reinforcement Learning

Advances in Neural Information Processing Systems 5, [NIPS Conference]
Reinforcement learning with a hierarchy of abstract models

AAAI'92 Proceedings of the tenth national conference on Artificial intelligence

Quantified Score

Hi-index	0.00

Visualization

Abstract

HEXQ is a reinforcement learning algorithm that decomposes a problem into subtasks and constructs a hierarchy using state variables. The maximum number of levels is constrained by the number of variables representing a state. In HEXQ, values learned for a subtask can be reused in different contexts if the subtasks are identical. If not, values for non-identical subtasks need to be trained separately. This paper introduces a method that tackles these two restrictions. Experimental results show that this method can save the training time dramatically.