Transfer Learning for Bilateral Multi Issue Negotiation

Siqi Chen; Haitham Bou Ammar; Karl Tuyls; Gerhard Weiss

Transfer Learning for Bilateral Multi Issue Negotiation

Siqi Chen, Haitham Bou Ammar, Karl Tuyls, Gerhard Weiss

Research output: Chapter in Book/Report/Conference proceeding › Conference article in proceeding › Academic › peer-review

Abstract

This paper proposes a novel strategy named Transfer between Negotiation Tasks (TNT) for automated bilateral negotiation with multiple issues. TNT is able to probabilistically transfer between different negotiation tasks in order to bias the target agent's learning behavior towards improved performance without unrealistic assumptions. We analyze the performance of our strategy and show that it substantially outperforms a powerful negotiation strategy across a variety of negotiation scenarios.

Original language	English
Title of host publication	Proceedings of BNAIC 2012:
Editors	Jos WHM Uiterwijk, Nico Roos, Mark HM Winands
Publisher	Maastricht University
Pages	59-66
Publication status	Published - 2012

Cite this

@inproceedings{3fe3a57b95e446c197cec2cea46c4c30,

title = "Transfer Learning for Bilateral Multi Issue Negotiation",

abstract = "This paper proposes a novel strategy named Transfer between Negotiation Tasks (TNT) for automated bilateral negotiation with multiple issues. TNT is able to probabilistically transfer between different negotiation tasks in order to bias the target agent's learning behavior towards improved performance without unrealistic assumptions. We analyze the performance of our strategy and show that it substantially outperforms a powerful negotiation strategy across a variety of negotiation scenarios.",

author = "Siqi Chen and Ammar, {Haitham Bou} and Karl Tuyls and Gerhard Weiss",

year = "2012",

language = "English",

pages = "59--66",

editor = "Uiterwijk, {Jos WHM} and Nico Roos and Winands, {Mark HM}",

booktitle = "Proceedings of BNAIC 2012:",

publisher = "Maastricht University",

address = "Netherlands",

}

TY - GEN

T1 - Transfer Learning for Bilateral Multi Issue Negotiation

AU - Chen, Siqi

AU - Ammar, Haitham Bou

AU - Tuyls, Karl

AU - Weiss, Gerhard

PY - 2012

Y1 - 2012

N2 - This paper proposes a novel strategy named Transfer between Negotiation Tasks (TNT) for automated bilateral negotiation with multiple issues. TNT is able to probabilistically transfer between different negotiation tasks in order to bias the target agent's learning behavior towards improved performance without unrealistic assumptions. We analyze the performance of our strategy and show that it substantially outperforms a powerful negotiation strategy across a variety of negotiation scenarios.

AB - This paper proposes a novel strategy named Transfer between Negotiation Tasks (TNT) for automated bilateral negotiation with multiple issues. TNT is able to probabilistically transfer between different negotiation tasks in order to bias the target agent's learning behavior towards improved performance without unrealistic assumptions. We analyze the performance of our strategy and show that it substantially outperforms a powerful negotiation strategy across a variety of negotiation scenarios.

M3 - Conference article in proceeding

SP - 59

EP - 66

BT - Proceedings of BNAIC 2012:

A2 - Uiterwijk, Jos WHM

A2 - Roos, Nico

A2 - Winands, Mark HM

PB - Maastricht University

ER -

Transfer Learning for Bilateral Multi Issue Negotiation

Abstract

Fingerprint

Cite this