کنفرانس بین المللی فناوری اطلاعات و دانش

صفحه اصلی / سیزدهمین کنفرانس بین المللی فناوری اطلاعات و دانش

LuckyAgent2022: A Stop-Learning Multi-Armed Bandit Automated Negotiating Agent

نویسندگان :

Arash Ebrahimnezhad¹ Faria Nassiri-Mofakham²

1- دانشگاه صنعتی نوشیروانی بابل 2- دانشگاه اصفهان

کلمات کلیدی :

Bilateral negotiation،automated negotiation agent

چکیده :

The 13th automated negotiation competition was held in 2 leagues (ANL2022 and SCML2022) in conjunction with the 31st IJCAI conference. The subject of ANL for 2022 is bilateral negotiation under the SOAP protocol. Additionally, agents were allowed to learn from their previous negotiations. The agents could have 3 main components: A Bidding strategy which decides which bid and when must be sent to the opponent, an Opponent model which tries to model the opponent's preferences, and an Acceptance strategy which decides whether to accept the opponent's offer or not. These three important components are known as the BOA framework. This paper explains LuckyAgent2022's BOA components and the learning methods over negotiation sessions.