Prediction for control delay on reinforcement learning

Junya Saito, Kazuyuki Narisawa, Ayumi Shinohara

Research output: Chapter in Book/Report/Conference proceedingConference contribution

1 Citation (Scopus)

Abstract

This paper addresses reinforcement learning problems with constant control delay, both for known case and unknown case. First, we propose an algorithm for known delay, which is a simple extension of the model-free learning algorithm introduced by (Schuitema et al., 2010). We extend it to predict current states explicitly, and empirically show that it is more efficient than existing algorithms. Next, we consider the case that the delay is unknown but its maximum value is bounded. We propose an algorithm using accuracy of prediction of states for this case. We show that the algorithm performs as efficient as the one which knows the real delay.

Original languageEnglish
Title of host publicationICAART 2012 - Proceedings of the 4th International Conference on Agents and Artificial Intelligence
Pages579-586
Number of pages8
Publication statusPublished - 2012 Jun 15
Event4th International Conference on Agents and Artificial Intelligence, ICAART 2012 - Vilamoura, Algarve, Portugal
Duration: 2012 Feb 62012 Feb 8

Publication series

NameICAART 2012 - Proceedings of the 4th International Conference on Agents and Artificial Intelligence
Volume1

Other

Other4th International Conference on Agents and Artificial Intelligence, ICAART 2012
Country/TerritoryPortugal
CityVilamoura, Algarve
Period12/2/612/2/8

Keywords

  • Control delay
  • Machine learning
  • Markov decision process
  • Reinforcement learning

ASJC Scopus subject areas

  • Artificial Intelligence

Fingerprint

Dive into the research topics of 'Prediction for control delay on reinforcement learning'. Together they form a unique fingerprint.

Cite this