Pre-Trained Models and Fine-Tuning for Negotiation Strategies with End-to-End Reinforcement Learning

Yuji Kobayashi, Katsuhide Fujita

2025

Abstract

In the field of automated negotiation, designing negotiation strategies handling any opponents is a key goal, and end-to-end reinforcement learning methods have been proposed. However, existing methods learn for each specific agent individually, which leads to the risk of overfitting to that agent, making it difficult to adapt to different situations or strategy changes even with the same agent. In addition, there is the issue that retraining is necessary from scratch when facing unknown opponents. To address these challenges, this study proposes a method that applies pre-training and fine-tuning to the model by an end-to-end reinforcement learning framework. Through evaluations, we demonstrate that the pre-trained model exhibits high generalizability. Furthermore, we show that fine-tuning the pre-trained model not only has the potential to further improve performance but also to have the potential to obtain high performance for unknown agents.

Paper Citation

in Harvard Style

Kobayashi Y. and Fujita K. (2025). Pre-Trained Models and Fine-Tuning for Negotiation Strategies with End-to-End Reinforcement Learning. In Proceedings of the 17th International Conference on Agents and Artificial Intelligence - Volume 1: ICAART; ISBN 978-989-758-737-5, SciTePress, pages 400-411. DOI: 10.5220/0013161500003890

in Bibtex Style

@conference{icaart25,
author={Yuji Kobayashi and Katsuhide Fujita},
title={Pre-Trained Models and Fine-Tuning for Negotiation Strategies with End-to-End Reinforcement Learning},
booktitle={Proceedings of the 17th International Conference on Agents and Artificial Intelligence - Volume 1: ICAART},
year={2025},
pages={400-411},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0013161500003890},
isbn={978-989-758-737-5},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 17th International Conference on Agents and Artificial Intelligence - Volume 1: ICAART
TI - Pre-Trained Models and Fine-Tuning for Negotiation Strategies with End-to-End Reinforcement Learning
SN - 978-989-758-737-5
AU - Kobayashi Y.
AU - Fujita K.
PY - 2025
SP - 400
EP - 411
DO - 10.5220/0013161500003890
PB - SciTePress