A Contextual Combinatorial Bandit Approach to Negotiation

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Li, Yexin, Mu, Zhancun, Qi, Siyuan
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913411482255360
author Li, Yexin
Mu, Zhancun
Qi, Siyuan
author_facet Li, Yexin
Mu, Zhancun
Qi, Siyuan
contents Learning effective negotiation strategies poses two key challenges: the exploration-exploitation dilemma and dealing with large action spaces. However, there is an absence of learning-based approaches that effectively address these challenges in negotiation. This paper introduces a comprehensive formulation to tackle various negotiation problems. Our approach leverages contextual combinatorial multi-armed bandits, with the bandits resolving the exploration-exploitation dilemma, and the combinatorial nature handles large action spaces. Building upon this formulation, we introduce NegUCB, a novel method that also handles common issues such as partial observations and complex reward functions in negotiation. NegUCB is contextual and tailored for full-bandit feedback without constraints on the reward functions. Under mild assumptions, it ensures a sub-linear regret upper bound. Experiments conducted on three negotiation tasks demonstrate the superiority of our approach.
format Preprint
id arxiv_https___arxiv_org_abs_2407_00567
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle A Contextual Combinatorial Bandit Approach to Negotiation
Li, Yexin
Mu, Zhancun
Qi, Siyuan
Artificial Intelligence
Machine Learning
Learning effective negotiation strategies poses two key challenges: the exploration-exploitation dilemma and dealing with large action spaces. However, there is an absence of learning-based approaches that effectively address these challenges in negotiation. This paper introduces a comprehensive formulation to tackle various negotiation problems. Our approach leverages contextual combinatorial multi-armed bandits, with the bandits resolving the exploration-exploitation dilemma, and the combinatorial nature handles large action spaces. Building upon this formulation, we introduce NegUCB, a novel method that also handles common issues such as partial observations and complex reward functions in negotiation. NegUCB is contextual and tailored for full-bandit feedback without constraints on the reward functions. Under mild assumptions, it ensures a sub-linear regret upper bound. Experiments conducted on three negotiation tasks demonstrate the superiority of our approach.
title A Contextual Combinatorial Bandit Approach to Negotiation
topic Artificial Intelligence
Machine Learning
url https://arxiv.org/abs/2407.00567