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

Takumu Shimizu, Ryota Higa, Toki Takahashi, Katsuhide Fujita, Shinji Nakadai

AAAI 2023 pp. 16326-16327

doi:10.1609/AAAI.V37I13.27023 /aaai/2023/shimizu2023aaai-scalable/

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.

PDF AAAI Semantic Scholar

Cite

Text

Shimizu et al. "Scalable Negotiating Agent Strategy via Multi-Issue Policy Network (Student Abstract)." AAAI Conference on Artificial Intelligence, 2023. doi:10.1609/AAAI.V37I13.27023

Markdown

[Shimizu et al. "Scalable Negotiating Agent Strategy via Multi-Issue Policy Network (Student Abstract)." AAAI Conference on Artificial Intelligence, 2023.](https://mlanthology.org/aaai/2023/shimizu2023aaai-scalable/) doi:10.1609/AAAI.V37I13.27023

BibTeX

@inproceedings{shimizu2023aaai-scalable,
  title     = {{Scalable Negotiating Agent Strategy via Multi-Issue Policy Network (Student Abstract)}},
  author    = {Shimizu, Takumu and Higa, Ryota and Takahashi, Toki and Fujita, Katsuhide and Nakadai, Shinji},
  booktitle = {AAAI Conference on Artificial Intelligence},
  year      = {2023},
  pages     = {16326-16327},
  doi       = {10.1609/AAAI.V37I13.27023},
  url       = {https://mlanthology.org/aaai/2023/shimizu2023aaai-scalable/}
}