Presentation 2015-06-18
Proposed stopping rule of exploration of Budget-limited multi-armed-bandit algorithm LAKUBE
Makoto Niimi, Takayuki Ito,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) We focus on the budget-limited multi-armed bandit(BL-MAB) problems. In BL-MAB problems, the agent's actions are costly and constrained by a fixed budget. LAKUBE is BL-MAB algorithm for highly budget-constrained situation. LAKUBE has parameter $K_alpha$ that limits the number of arms of exploration. But, $K_alpha$ need to set optimal value. We propose new BL-MAB algorithm seKUBE. seKUBE decides to the number of arms of exploration. In our experiments, we compared the existing bandit algorithm with our proposedbandit algorithm.
Keyword(in Japanese) (See Japanese page)
Keyword(in English)
Paper # AI2015-10
Date of Issue 2015-06-11 (AI)

Conference Information
Committee AI
Conference Date 2015/6/18(1days)
Place (in Japanese) (See Japanese page)
Place (in English)
Topics (in Japanese) (See Japanese page)
Topics (in English)
Chair Toshiharu Sugawara(Waseda Univ.)
Vice Chair Tsunenori Mine(Kyushu Univ.) / Daisuke Katagami(Tokyo Polytechnic Univ.)
Secretary Tsunenori Mine(Kyoto Univ.) / Daisuke Katagami(Shizuoka Univ.)
Assistant Yuichi Sei(Univ. of Electro-Comm.)

Paper Information
Registration To Technical Committee on Artificial Intelligence and Knowledge-Based Processing
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Proposed stopping rule of exploration of Budget-limited multi-armed-bandit algorithm LAKUBE
Sub Title (in English)
Keyword(1)
Keyword(2)
Keyword(3)
1st Author's Name Makoto Niimi
1st Author's Affiliation Nagoya Institute of Technology(NIT)
2nd Author's Name Takayuki Ito
2nd Author's Affiliation Nagoya Institute of Technology(NIT)
Date 2015-06-18
Paper # AI2015-10
Volume (vol) vol.115
Number (no) AI-97
Page pp.pp.55-60(AI),
#Pages 6
Date of Issue 2015-06-11 (AI)