Optimal Online Learning Procedures for Model-Free Policy Evaluation

Authors:
Tsuyoshi Ueno;Shin-Ichi Maeda;Motoaki Kawanabe;Shin Ishii
Affiliations:
Graduate School of Informatics, Kyoto University,;Graduate School of Informatics, Kyoto University,;Fraunhofer FIRST and Berlin Institute of Technology, Germany;Graduate School of Informatics, Kyoto University,
Venue:
ECML PKDD '09 Proceedings of the European Conference on Machine Learning and Knowledge Discovery in Databases: Part II
Year:
2009

Citing 11
Cited 0

Matrix analysis

Matrix analysis
Linear least-squares algorithms for temporal difference learning

Machine Learning - Special issue on reinforcement learning
Natural gradient works efficiently in learning

Neural Computation
Introduction to Reinforcement Learning

Introduction to Reinforcement Learning
Neuro-Dynamic Programming

Neuro-Dynamic Programming
Technical Update: Least-Squares Temporal Difference Learning

Machine Learning
Least Squares Policy Evaluation Algorithms with Linear Function Approximation

Discrete Event Dynamic Systems
Bias and variance in value function estimation

ICML '04 Proceedings of the twenty-first international conference on Machine learning
On-line learning for very large data sets: Research Articles

Applied Stochastic Models in Business and Industry - Statistical Learning
Proto-value Functions: A Laplacian Framework for Learning Representation and Control in Markov Decision Processes

The Journal of Machine Learning Research
A semiparametric statistical approach to model-free policy evaluation

Proceedings of the 25th international conference on Machine learning

Quantified Score

Hi-index	0.00

Visualization

Abstract

In this study, we extend the framework of semiparametric statistical inference introduced recently to reinforcement learning [1] to online learning procedures for policy evaluation. This generalization enables us to investigate statistical properties of value function estimators both by batch and online procedures in a unified way in terms of estimating functions. Furthermore, we propose a novel online learning algorithm with optimal estimating functions which achieve the minimum estimation error. Our theoretical developments are confirmed using a simple chain walk problem.