Online Reinforcement Learning to Search the Shortest Path in Maze Environments 


Vol. 9,  No. 2, pp. 155-162, Apr.  2002
10.3745/KIPSTB.2002.9.2.155


PDF
  Abstract

Reinforcement learning is a learning method that uses trial-and-error to perform learning by interacting with dynamic environments. It is classified into online reinforcement learning and delayed reinforcement learning. In this paper, we propose an online reinforcement learning system (ONRELS : ONline REinforcement Learning System). ONRELS updates the estimate-value about all the selectable (state, action) pairs before making state-transition at the current state. The ONRELS learns by interacting with the compressed environments through trial-and-error after it compresses the state space of the maze environments. Through experiments, we can see that ONRELS can search the shortest path faster than Q-learning using TD-error and Q(λ)-learning using TD(λ) in the maze environments.

  Statistics
  Cite this article

[IEEE Style]

B. C. Kim, S. K. Kim, B. J. Yoon, "Online Reinforcement Learning to Search the Shortest Path in Maze Environments," The KIPS Transactions:PartB , vol. 9, no. 2, pp. 155-162, 2002. DOI: 10.3745/KIPSTB.2002.9.2.155.

[ACM Style]

Byung Cheon Kim, Sam Keun Kim, and Byung Joo Yoon. 2002. Online Reinforcement Learning to Search the Shortest Path in Maze Environments. The KIPS Transactions:PartB , 9, 2, (2002), 155-162. DOI: 10.3745/KIPSTB.2002.9.2.155.

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