Presentation 2010/6/11
On the Tug-of-war Model for Multi-armed Bandit Problem : Bio-inspired Computing Method for Nonlocally-correlated Parallel Searches
Song-Ju KIM, Masashi AONO, Masahiko HARA,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) The "tug-of-war (TOW) model" proposed in this study is a unique method for parallel searches inspired by the photoavoidance behavior of the single-celled amoeba, the true slime mold Physarum. In the TOW model, many branches of the amoeba act as search agents to collect information on light stimulations while conserving the total sum of their resources. We show that the "nonlocal correlation" via resource conservation can be advantageous to manage the "exploration-exploitation dilemma" for solving the multi-armed bandit problem. We also show the effect of the information on light stimulations from other branches on the TOW model's performance.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Reinforcement learning / multi-armed bandit problem / bio-inspired computing / parallel search
Paper # NC2010-4,NLP2010-4
Date of Issue

Conference Information
Committee NC
Conference Date 2010/6/11(1days)
Place (in Japanese) (See Japanese page)
Place (in English)
Topics (in Japanese) (See Japanese page)
Topics (in English)
Chair
Vice Chair
Secretary
Assistant

Paper Information
Registration To Neurocomputing (NC)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) On the Tug-of-war Model for Multi-armed Bandit Problem : Bio-inspired Computing Method for Nonlocally-correlated Parallel Searches
Sub Title (in English)
Keyword(1) Reinforcement learning
Keyword(2) multi-armed bandit problem
Keyword(3) bio-inspired computing
Keyword(4) parallel search
1st Author's Name Song-Ju KIM
1st Author's Affiliation Flucto-Order Functions Research Team, RIKEN-HYU Collaboration Research Center, ASI, RIKEN()
2nd Author's Name Masashi AONO
2nd Author's Affiliation Flucto-Order Functions Research Team, RIKEN-HYU Collaboration Research Center, ASI, RIKEN
3rd Author's Name Masahiko HARA
3rd Author's Affiliation Flucto-Order Functions Research Team, RIKEN-HYU Collaboration Research Center, ASI, RIKEN
Date 2010/6/11
Paper # NC2010-4,NLP2010-4
Volume (vol) vol.110
Number (no) 83
Page pp.pp.-
#Pages 6
Date of Issue