Parallel Reinforcement Learning for Weighted Multi-criteria Model with Adaptive Margin

Authors:
Kazuyuki Hiraoka;Manabu Yoshida;Taketoshi Mishima
Affiliations:
Saitama University, Saitama-shi, Japan;Saitama University, Saitama-shi, Japan;Saitama University, Saitama-shi, Japan
Venue:
Neural Information Processing
Year:
2007

Citing 4
Cited 1

Computational geometry: an introduction

Computational geometry: an introduction
Introduction to Reinforcement Learning

Introduction to Reinforcement Learning
Dynamic preferences in multi-criteria reinforcement learning

ICML '05 Proceedings of the 22nd international conference on Machine learning
On the convergence of stochastic iterative dynamic programming algorithms

Neural Computation

Multi-policy optimization in self-organizing systems

SOAR'09 Proceedings of the First international conference on Self-organizing architectures

Quantified Score

Hi-index	0.00

Visualization

Abstract

Reinforcement learning (RL) for a linear family of tasks is studied in this paper. The key of our discussion is nonlinearity of the optimal solution even if the task family is linear; we cannot obtain the optimal policy by a naive approach. Though there exists an algorithm for calculating the equivalent result to Q-learning for each task all together, it has a problem with explosion of set sizes. We introduce adaptive margins to overcome this difficulty.