Learning to manage risks in non-cooperative dialogues

Ioannis Efstathiou, Oliver Lemon

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

We investigate statistical dialogue agents which learn to perform non-cooperative dialogue moves in order to complete their own objectives in a stochastic trading game. We show that, when given the ability to perform both cooperative and non-cooperative dialogue moves, such an agent can learn to bluff and to lie so as to win games more often - against a variety of adversaries, and under various conditions such as risking penalties for being caught in deception. Here we present new results showing how learned non-cooperative dialogue strategies change depending on a) how severe the penalty is for being caught being non-cooperative, and b) how risky the non-cooperative behaviour is (i.e. the probability of being caught). For example, we show that a non-cooperative dialogue agent can learn to win an additional 4.5% of games against a strong rule-based adversary, even when there is an additional 10% chance of being caught (exposed) every time it attempts a non-cooperative (manipulative) move, when the penalty for being caught is that the adversary will no longer trade.
Original languageEnglish
Title of host publicationSemDial 2014 Proceedings
EditorsVerena Rieser, Philippe Muller
Pages173-175
Number of pages3
Publication statusPublished - 1 Sep 2014
Event18th Workshop on the Semantics and Pragmatics of Dialogue - Heriot Watt University, Edinburgh, United Kingdom
Duration: 1 Sep 20143 Sep 2014

Publication series

NameProceedings (SemDial)
ISSN (Print)2308-2275

Workshop

Workshop18th Workshop on the Semantics and Pragmatics of Dialogue
Abbreviated titleSemDial 2014
CountryUnited Kingdom
CityEdinburgh
Period1/09/143/09/14

Cite this

Efstathiou, I., & Lemon, O. (2014). Learning to manage risks in non-cooperative dialogues. In V. Rieser, & P. Muller (Eds.), SemDial 2014 Proceedings (pp. 173-175). (Proceedings (SemDial)).