Efficient experience reuse in non-Markovian environments

Le Tien Dung, Takashi Komeda, Motoki Takagi

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

4 Citations (Scopus)

Abstract

Learning time is always a critical issue in Reinforcement Learning, especially when Recurrent Neural Networks are used to predict Q values in non-Markovian environments. Experience reuse has been received much attention due to its ability to reduce learning time. In this paper, we propose a new method to efficiently reuse experience. Our method generates new episodes from recorded episodes using an action-pair merger. Recorded episodes and new episodes are replayed after each learning epoch. We compare our method with standard online learning, and learning using experience replay in a vision-based robot problem. The results show the potential of this approach.

Original languageEnglish
Title of host publicationProceedings of SICE Annual Conference 2008 - International Conference on Instrumentation, Control and Information Technology
Pages3327-3332
Number of pages6
DOIs
Publication statusPublished - 2008 Dec 1
EventSICE Annual Conference 2008 - International Conference on Instrumentation, Control and Information Technology - Tokyo, Japan
Duration: 2008 Aug 202008 Aug 22

Publication series

NameProceedings of the SICE Annual Conference

Conference

ConferenceSICE Annual Conference 2008 - International Conference on Instrumentation, Control and Information Technology
CountryJapan
CityTokyo
Period08/8/2008/8/22

Keywords

  • Recurrent neural networks
  • Reinforcement learning

ASJC Scopus subject areas

  • Control and Systems Engineering
  • Computer Science Applications
  • Electrical and Electronic Engineering

Fingerprint Dive into the research topics of 'Efficient experience reuse in non-Markovian environments'. Together they form a unique fingerprint.

  • Cite this

    Dung, L. T., Komeda, T., & Takagi, M. (2008). Efficient experience reuse in non-Markovian environments. In Proceedings of SICE Annual Conference 2008 - International Conference on Instrumentation, Control and Information Technology (pp. 3327-3332). [4655239] (Proceedings of the SICE Annual Conference). https://doi.org/10.1109/SICE.2008.4655239