Presentation	2001/7/16 Algorithm for Learning Negotiation Strategy with Reinforcement Learning Leo OHTAKE, Toyoaki NISHIDA,
PDF Download Page	PDF download Page Link
Abstract(in Japanese)	(See Japanese page)
Abstract(in English)	In this paper, we propose an algorithm for self-bidding agents in the internet auction to learn bidding strategy depending on the circumstances. Q-learning and e-greedy methods, the typical techniques in reinforcement learning, are used in learning and decision-making modules which are the basis of this algorithm. We applied this algorithm to an ascending-bid auction, and the agents could acquire the bidding strategy to get higher utility in one successful bid.
Keyword(in Japanese)	(See Japanese page)
Keyword(in English)	auction / self-bidding agent / bidding strategy / reinforcement learning / utility
Paper #	OFS2001-11,AI2001-16
Date of Issue

Conference Information
Committee	AI
Conference Date	2001/7/16(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	Artificial Intelligence and Knowledge-Based Processing (AI)
Language	JPN
Title (in Japanese)	(See Japanese page)
Sub Title (in Japanese)	(See Japanese page)
Title (in English)	Algorithm for Learning Negotiation Strategy with Reinforcement Learning
Sub Title (in English)
Keyword(1)	auction
Keyword(2)	self-bidding agent
Keyword(3)	bidding strategy
Keyword(4)	reinforcement learning
Keyword(5)	utility
1st Author's Name	Leo OHTAKE
1st Author's Affiliation	Department of Information and Communication Engineering, Graduate school of Information Technology, The University of Tokyo.()
2nd Author's Name	Toyoaki NISHIDA
2nd Author's Affiliation	Department of Information and Communication Engineering, Graduate school of Information Technology, The University of Tokyo.
Date	2001/7/16
Paper #	OFS2001-11,AI2001-16
Volume (vol)	vol.101
Number (no)	210
Page	pp.pp.-
#Pages	8
Date of Issue