Scalable Negotiating Agent Strategy via Multi-Issue Policy Network (Student Abstract)

Authors

  • Takumu Shimizu Tokyo University of Agriculture and Technology National Institute of Advanced Industrial Science and Technology
  • Ryota Higa National Institute of Advanced Industrial Science and Technology NEC Data Science Research Laboratories
  • Toki Takahashi Tokyo University of Agriculture and Technology National Institute of Advanced Industrial Science and Technology
  • Katsuhide Fujita Tokyo University of Agriculture and Technology National Institute of Advanced Industrial Science and Technology
  • Shinji Nakadai National Institute of Advanced Industrial Science and Technology NEC Data Science Research Laboratories

DOI:

https://doi.org/10.1609/aaai.v37i13.27023

Keywords:

Reinforcement Learning, Automated Negotiation, Deep Neural Network, Multi-issue Policy Network

Abstract

Previous research on the comprehensive negotiation strategy using deep reinforcement learning (RL) has scalability issues of not performing effectively in the large-sized domains. We improve negotiation strategy via deep RL by considering an issue-based represented deep policy network to deal with multi-issue negotiation. The architecture of the proposed learning agent considers the characteristics of multi-issue negotiation domains and policy-based learning. We demonstrate that proposed method achieve equivalent or higher utility than existing negotiation agents in the large-sized domains.
AAAI-23 Proceedings Cover

Downloads

Published

2024-07-15

How to Cite

Shimizu, T., Higa, R., Takahashi, T., Fujita, K., & Nakadai, S. (2024). Scalable Negotiating Agent Strategy via Multi-Issue Policy Network (Student Abstract). Proceedings of the AAAI Conference on Artificial Intelligence, 37(13), 16326-16327. https://doi.org/10.1609/aaai.v37i13.27023

Issue

Vol. 37 No. 13: AAAI-23 Special Programs, IAAI-23, EAAI-23, Student Papers and Demonstrations

Section

AAAI Student Abstract and Poster Program