Function Approximation for Reinforcement Learning using Fuzzy Clustering 


Vol. 10,  No. 6, pp. 587-592, Oct.  2003
10.3745/KIPSTB.2003.10.6.587


PDF
  Abstract

Many real world control problems have continuous states and actions. When the state space is continuous, the reinforcement learning problems involve very large state space and suffer from memory and time for learning all individual state-action values. These problems need function approximators that reason action about new state from previously experienced states. We introduce Fuzzy Q-Map that is a function approximators for 1 - step Q-learning and is based on fuzzy clustering. Fuzzy Q-Map groups similar states and chooses an action and refers Q value according to membership degree. The centroid and Q value of winner cluster is updated using membership degree and TD(Temporal Difference) error. We applied Fuzzy Q-Map to the mountain car problem and acquired accelerated learning speed.

  Statistics
  Cite this article

[IEEE Style]

L. Y. A, J. G. Sug, J. T. Chung, "Function Approximation for Reinforcement Learning using Fuzzy Clustering," The KIPS Transactions:PartB , vol. 10, no. 6, pp. 587-592, 2003. DOI: 10.3745/KIPSTB.2003.10.6.587.

[ACM Style]

Lee Yeong A, Jeong Gyeong Sug, and Jeong Tae Chung. 2003. Function Approximation for Reinforcement Learning using Fuzzy Clustering. The KIPS Transactions:PartB , 10, 6, (2003), 587-592. DOI: 10.3745/KIPSTB.2003.10.6.587.

Forms

Search
(IN TITLE, AUTHOR, ABSTRACT,KEYWORDS)

Advanced Search ▼

POPULAR KEYWORDS
(TOP 10 KEYWORDS)

Recent Publications
(LAST 3 YEARS)

Old Journals

Indexing

All publications of TKIPS is indexed in DOI, EBSCO, Google Scholar, Crossref, and CrossCheck.

TKIPS is also selected as the Journal for Accreditation by NRF (National Research Foundation of Korea).

Related Journals