Reinforcement learning in multi-dimensional state-action space using random rectangular coarse coding and Gibbs sampling

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

13 Citations (Scopus)

Abstract

This paper presents a coarse coding technique and an action selection scheme for reinforcement learning (RL) in multi-dimensional and continuous state-action spaces following conventional and sound RL manners. RL in high-dimensional continuous domains includes two issues: One is a generalization problem for value-function approximation, and the other is a sampling problem for action selection over multi-dimensional continuous action spaces. The proposed method combines random rectangular coarse coding with an action selection scheme using Gibbs-sampling. The random rectangular coarse coding is very simple and quite suited both to approximate Q-functions in high-dimensional spaces and to execute Gibbs sampling. Gibbs sampling enables us to execute action selection following Boltsmann distribution over high-dimensional action space. The algorithm is demonstrated through Rod in maze problem and a redundant-arm reaching task comparing with conventional regular grid approaches.

Original languageEnglish
Title of host publicationProceedings of the 2007 IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS 2007
Pages88-95
Number of pages8
DOIs
Publication statusPublished - 2007
Event2007 IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS 2007 - San Diego, CA, United States
Duration: Oct 29 2007Nov 2 2007

Publication series

NameIEEE International Conference on Intelligent Robots and Systems

Other

Other2007 IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS 2007
CountryUnited States
CitySan Diego, CA
Period10/29/0711/2/07

All Science Journal Classification (ASJC) codes

  • Control and Systems Engineering
  • Software
  • Computer Vision and Pattern Recognition
  • Computer Science Applications

Fingerprint Dive into the research topics of 'Reinforcement learning in multi-dimensional state-action space using random rectangular coarse coding and Gibbs sampling'. Together they form a unique fingerprint.

Cite this