ICRA'09 Paper Abstract

Close

Paper FrD6.2

Sugiyama, Masashi (Tokyo Institute of Technology), Hachiya, Hirotaka (Tokyo Institute of Technology), Kashima, Hisashi (IBM Research), Morimura, Tetsuro (IBM Research)

Least Absolute Policy Iteration for Robust Value Function Approximation

Scheduled for presentation during the Regular Sessions "Learning and Adaptive Systems - IV" (FrD6), Friday, May 15, 2009, 15:50−16:10, Room: 404

2009 IEEE International Conference on Robotics and Automation, May 12 - 17, 2009, Kobe, Japan

This information is tentative and subject to change. Compiled on January 24, 2022

Keywords Adaptive Control, Learning and Adaptive Systems, Risk Management

Abstract

Least-squares policy iteration is a useful reinforcement learning method in robotics due to its computational efficiency. However, it tends to be sensitive to outliers in observed rewards. In this paper, we propose an alternative method that employs the absolute loss for enhancing robustness and reliability. The proposed method is formulated as a linear programming problem which can be solved efficiently by standard optimization software, so the computational advantage is not sacrificed for gaining robustness and reliability. We demonstrate the usefulness of the proposed approach through simulated robot-control tasks.

 

 

Technical Content © IEEE Robotics & Automation Society

This site is protected by copyright and trademark laws under US and International law.
All rights reserved. © 2002-2022 PaperCept, Inc.
Page generated 2022-01-24  07:11:06 PST  Terms of use