Multiple Model-Based Reinforcement Learning

Article Properties
  • Language
    English
  • Publication Date
    2002/06/01
  • Indian UGC (Journal)
  • Refrences
    17
  • Citations
    208
  • Kenji Doya Human Information Science Laboratories, ATR International, Seika, Soraku, Kyoto 619-0288, Japan; CREST, Japan Science and Technology Corporation, Seika, Soraku, Kyoto 619-0288, Japan; Kawato Dynamic Brain Project, ERATO, Japan Science and Technology Corporation, Seika, Soraku, Kyoto 619-0288, Japan; and Nara Institute of Science and Technology, Ikoma, Nara 630-0101, Japan,
  • Kazuyuki Samejima Human Information Science Laboratories, ATR International, Seika, Soraku, Kyoto 619-0288, Japan, and Kawato Dynamic Brain Project, ERATO, Japan Science and Technology Corporation, Seika, Soraku, Kyoto 619-0288, Japan,
  • Ken-ichi Katagiri ATR Human Information Processing Research Laboratories, Seika, Soraku, Kyoto 619-0288, Japan, and Nara Institute of Science and Technology, Ikoma, Nara 630-0101, Japan,
  • Mitsuo Kawato Human Information Science Laboratories, ATR International, Seika, Soraku, Kyoto 619-0288, Japan; Kawato Dynamic Brain Project, ERATO, Japan Science and Technology Corporation, Seika, Soraku, Kyoto 619-0288, Japan; and Nara Institute of Science and Technology, Ikoma, Nara 630-0101, Japan,
Abstract
Cite
Doya, Kenji, et al. “Multiple Model-Based Reinforcement Learning”. Neural Computation, vol. 14, no. 6, 2002, pp. 1347-69, https://doi.org/10.1162/089976602753712972.
Doya, K., Samejima, K., Katagiri, K.- ichi, & Kawato, M. (2002). Multiple Model-Based Reinforcement Learning. Neural Computation, 14(6), 1347-1369. https://doi.org/10.1162/089976602753712972
Doya K, Samejima K, Katagiri K ichi, Kawato M. Multiple Model-Based Reinforcement Learning. Neural Computation. 2002;14(6):1347-69.
Journal Categories
Medicine
Internal medicine
Neurosciences
Biological psychiatry
Neuropsychiatry
Science
Mathematics
Instruments and machines
Electronic computers
Computer science
Technology
Electrical engineering
Electronics
Nuclear engineering
Electronics
Technology
Mechanical engineering and machinery
Description

Improving reinforcement learning for complex control: This research introduces a modular reinforcement learning architecture called Multiple Model-Based Reinforcement Learning (MMRL) designed for nonlinear, nonstationary control tasks. It decomposes complex tasks into multiple domains based on the predictability of environmental dynamics. The system comprises multiple modules, each with a state prediction model and a reinforcement learning controller. A “responsibility signal,” derived from the softmax function of prediction errors, weights module outputs and gates the learning of prediction models and controllers. The authors formulate MMRL for discrete-time, finite-state cases and continuous-time, continuous-state cases. MMRL's performance is demonstrated in a nonstationary hunting task in a grid world (discrete case) and in swinging up a pendulum with variable physical parameters (continuous case), highlighting its effectiveness for challenging control problems.

This Neural Computation publication aligns perfectly with the journal’s emphasis on theoretical and computational approaches to understanding neural and cognitive systems. By proposing a novel reinforcement learning architecture, the paper advances the field of machine learning and offers a new perspective on how complex control tasks can be tackled, which will engage a significant portion of the readership.

Refrences
Citations
Citations Analysis
The first research to cite this article was titled Context-Dependent Anticipation of Different Task Dynamics: Rapid Recall of Appropriate Motor Skills Using Visual Cues and was published in 2003. The most recent citation comes from a 2024 study titled Context-Dependent Anticipation of Different Task Dynamics: Rapid Recall of Appropriate Motor Skills Using Visual Cues . This article reached its peak citation in 2021 , with 18 citations.It has been cited in 109 different journals, 18% of which are open access. Among related journals, the Neural Networks cited this research the most, with 17 citations. The chart below illustrates the annual citation trends for this article.
Citations used this article by year