Abstract
This paper introduces an acceptance strategy based on reinforcement learning for automated bilateral negotiation, where negotiating agents bargain on multiple issues in a variety of negotiation scenarios. Several acceptance strategies based on predefined rules have been introduced in the automated negotiation literature. Those rules mostly rely on some heuristics, which take time and/or utility into account. For some negotiation settings, an acceptance strategy solely based on a negotiation deadline might perform well; however, it might fail in another setting. Instead of following predefined acceptance rules, this paper presents an acceptance strategy that aims to learn whether to accept its opponent's offer or make a counter offer by reinforcement signals received after performing an action. In an experimental setup, it is shown that the performance of the proposed approach improves over time.
Highlights
Automated negotiation [1] is an important study field in artificial intelligence, where intelligent agents negotiate on behalf of their users on multiple issues with the aim of maximizing their own utility
While our work proposes using RL for the acceptance strategy, other works using RL in automated negotiations mostly focus on learning a bidding strategy or negotiation strategy
This paper proposes a novel acceptance strategy model for bilateral negotiations based on deep RL
Summary
Automated negotiation [1] is an important study field in artificial intelligence, where intelligent agents negotiate on behalf of their users on multiple issues with the aim of maximizing their own utility. The turn-taking fashion of taking actions in automated negotiation makes it an appropriate environment for applying reinforcement learning [9] (RL), where the agents can learn the best actions to be taken based on the feedback given during these interactions. Our negotiating agent employs RL in order to determine whether or not it should accept its opponent’s current offer. It accepts the given offer or makes a counter offer. It is observed that our agent learns what to bid and when to accept its opponents counter offer and improves its performance over time.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
More From: TURKISH JOURNAL OF ELECTRICAL ENGINEERING & COMPUTER SCIENCES
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.