Using Gaussian Processes to Optimise Concession in Complex Negotiations Against Unknown Opponents
Abstract
In multi-issue automated negotiation against unknown opponents, a key part of effective negotiation is the choice of concession strategy. In this paper, we develop a principled concession strategy, based on Gaussian processes predicting the opponent's future behaviour. We then use this to set the agent's concession rate dynamically during a single negotiation session. We analyse the performance of our strategy and show that it outperforms the state-of-the-art negotiating agents from the 2010 Automated Negotiating Agents Competition, in both a tournament setting and in self-play, across a variety of negotiation domains.
Cite
Text
Williams et al. "Using Gaussian Processes to Optimise Concession in Complex Negotiations Against Unknown Opponents." International Joint Conference on Artificial Intelligence, 2011. doi:10.5591/978-1-57735-516-8/IJCAI11-080Markdown
[Williams et al. "Using Gaussian Processes to Optimise Concession in Complex Negotiations Against Unknown Opponents." International Joint Conference on Artificial Intelligence, 2011.](https://mlanthology.org/ijcai/2011/williams2011ijcai-using/) doi:10.5591/978-1-57735-516-8/IJCAI11-080BibTeX
@inproceedings{williams2011ijcai-using,
title = {{Using Gaussian Processes to Optimise Concession in Complex Negotiations Against Unknown Opponents}},
author = {Williams, Colin R. and Robu, Valentin and Gerding, Enrico H. and Jennings, Nicholas R.},
booktitle = {International Joint Conference on Artificial Intelligence},
year = {2011},
pages = {432-438},
doi = {10.5591/978-1-57735-516-8/IJCAI11-080},
url = {https://mlanthology.org/ijcai/2011/williams2011ijcai-using/}
}