Introduction and control of subgoals in reinforcement learning

Authors:
Junichi Murata;Yasuomi Abe;Keisuke Ota
Affiliations:
Department of Electrical and Electronic Systems Engineering, Kyushu University, Fukuoka, Japan;Department of Electrical and Electronic Systems Engineering, Kyushu University, Fukuoka, Japan;Department of Electrical and Electronic Systems Engineering, Kyushu University, Fukuoka, Japan
Venue:
AIAP'07 Proceedings of the 25th conference on Proceedings of the 25th IASTED International Multi-Conference: artificial intelligence and applications
Year:
2007

Citing 5
Cited 0

Introduction to Reinforcement Learning

Introduction to Reinforcement Learning
Automatic Discovery of Subgoals in Reinforcement Learning using Diverse Density

ICML '01 Proceedings of the Eighteenth International Conference on Machine Learning
Practical Reinforcement Learning in Continuous Spaces

ICML '00 Proceedings of the Seventeenth International Conference on Machine Learning
HQ-Learning: Discovering Markovian Subgoals for Non-Markovian Reinforcement Learning

HQ-Learning: Discovering Markovian Subgoals for Non-Markovian Reinforcement Learning
Integrating Guidance into Relational Reinforcement Learning

Machine Learning

Quantified Score

Hi-index	0.00

Visualization

Abstract

Reinforcement learning (RL) can be applied to a wide class of problems because it requires no other information than perceived states and rewards to find good action policies. However, it takes a large number of trials before acquiring the optimal policy. In order to make RL faster, use of subgoals is proposed. Since errors and ambiguity are inevitable in subgoal information provided by human designers, a mechanism is proposed that controls use of subgoals. The method is applied to examples and the results show that use of subgoals is very effective in accelerating RL and that the proposed control mechanism successfully suppresses possible critical damages on the RL performance caused by errors and ambiguity in subgoal information.