IAMhaggler2011: A Gaussian Process Regression Based Negotiation Agent
We describe the strategy used by our agent, IAMhaggler2011, which finished in third place in the 2011 Automated Negotiating Agent Competition. A key feature of this agent is the way in which it models the likely negotiation behaviour of its opponent. Specifically, it first uses a Gaussian process regression technique to estimate the future concession of its negotiation opponent. Its concession is then set as a best response to this prediction.
KeywordsGaussian Process Expected Utility Negotiation Behaviour Target Utility Concession Strategy
Unable to display preview. Download preview PDF.
- 1.Baarslag, T., Hindriks, K., Jonker, C.M., Kraus, S., Lin, R.: The second automated negotiating agents competition (ANAC 2011). In: Complex Automated Negotiations. SCI, vol. 435, pp. 183–197. Springer, Heidelberg (2012)Google Scholar
- 2.Rasmussen, C.E., Williams, C.K.I.: Gaussian Processes for Machine Learning. The MIT Press (2006)Google Scholar
- 3.Williams, C.R., Robu, V., Gerding, E.H., Jennings, N.R.: IAMhaggler: A Negotiation Agent for Complex Environments. In: Ito, T., Zhang, M., Robu, V., Fatima, S., Matsuo, T. (eds.) New Trends in Agent-Based Complex Automated Negotiations. SCI, vol. 383, pp. 151–158. Springer, Heidelberg (2012)Google Scholar
- 4.Williams, C.R., Robu, V., Gerding, E.H., Jennings, N.R.: Using gaussian processes to optimise concession in complex negotiations against unknown opponents. In: Proc. of the Twenty-Second International Joint Conference on Artificial Intelligence, vol. 1, pp. 432–438 (2011)Google Scholar