ANEGMA : an automated negotiation model for e-markets. / Bagga, Pallavi; Paoletti, Nicola; Alrayes, Bedour; Stathis, Kostas.

In: Autonomous Agents and Multi-Agent Systems, Vol. 35, 27, 07.06.2021.

Research output: Contribution to journalArticlepeer-review

Published

Standard

ANEGMA : an automated negotiation model for e-markets. / Bagga, Pallavi; Paoletti, Nicola; Alrayes, Bedour; Stathis, Kostas.

In: Autonomous Agents and Multi-Agent Systems, Vol. 35, 27, 07.06.2021.

Research output: Contribution to journalArticlepeer-review

Harvard

APA

Vancouver

Author

BibTeX

@article{e17c3c2e5d6b4ebfa795a173a27b4a14,
title = "ANEGMA: an automated negotiation model for e-markets",
abstract = "We present a novel negotiation model that allows an agent to learn how to negotiate during concurrent bilateral negotiations in unknown and dynamic e-markets. The agent uses an actor-critic architecture with model-free reinforcement learning to learn a strategy expressed as a deep neural network. We pre-train the strategy by supervision from synthetic market data, thereby decreasing the exploration time required for learning during negotiation. As a result, we can build automated agents for concurrent negotiations that can adapt to different e-market settings without the need to be pre-programmed. Our experimental evaluation shows that our deep reinforcement learning based agents outperform two existing well-known negotiation strategies in one-to-many concurrent bilateral negotiations for a range of e-market settings.",
author = "Pallavi Bagga and Nicola Paoletti and Bedour Alrayes and Kostas Stathis",
year = "2021",
month = jun,
day = "7",
doi = "10.1007/s10458-021-09513-x",
language = "English",
volume = "35",
journal = "Autonomous Agents and Multi-Agent Systems",
issn = "1387-2532",
publisher = "Springer",

}

RIS

TY - JOUR

T1 - ANEGMA

T2 - an automated negotiation model for e-markets

AU - Bagga, Pallavi

AU - Paoletti, Nicola

AU - Alrayes, Bedour

AU - Stathis, Kostas

PY - 2021/6/7

Y1 - 2021/6/7

N2 - We present a novel negotiation model that allows an agent to learn how to negotiate during concurrent bilateral negotiations in unknown and dynamic e-markets. The agent uses an actor-critic architecture with model-free reinforcement learning to learn a strategy expressed as a deep neural network. We pre-train the strategy by supervision from synthetic market data, thereby decreasing the exploration time required for learning during negotiation. As a result, we can build automated agents for concurrent negotiations that can adapt to different e-market settings without the need to be pre-programmed. Our experimental evaluation shows that our deep reinforcement learning based agents outperform two existing well-known negotiation strategies in one-to-many concurrent bilateral negotiations for a range of e-market settings.

AB - We present a novel negotiation model that allows an agent to learn how to negotiate during concurrent bilateral negotiations in unknown and dynamic e-markets. The agent uses an actor-critic architecture with model-free reinforcement learning to learn a strategy expressed as a deep neural network. We pre-train the strategy by supervision from synthetic market data, thereby decreasing the exploration time required for learning during negotiation. As a result, we can build automated agents for concurrent negotiations that can adapt to different e-market settings without the need to be pre-programmed. Our experimental evaluation shows that our deep reinforcement learning based agents outperform two existing well-known negotiation strategies in one-to-many concurrent bilateral negotiations for a range of e-market settings.

U2 - 10.1007/s10458-021-09513-x

DO - 10.1007/s10458-021-09513-x

M3 - Article

VL - 35

JO - Autonomous Agents and Multi-Agent Systems

JF - Autonomous Agents and Multi-Agent Systems

SN - 1387-2532

M1 - 27

ER -