Abstract
Recent work has learned non-cooperative dialogue behaviour within a stochastic trading game, including dialogue moves such as bluffing and lying. Here, we introduce an adversary which can detect deception based on logical contradictions between dialogue moves. Being caught in deception, the adversary will penalise this behaviour by either refusing to trade or declaring victory. We compare our results to a learning agent trained with a gullible adversary and show that a more realistic adversary decreases the chances of winning by over 20%, if the penalty for cheating is to lose the game. In future work we will re-train the learning agent within this more challenging environment.
Original language | English |
---|---|
Title of host publication | SemDial 2014 Proceedings |
Editors | Verena Rieser, Philippe Muller |
Pages | 252-254 |
Number of pages | 3 |
Publication status | Published - 1 Sep 2014 |
Event | 18th Workshop on the Semantics and Pragmatics of Dialogue - Heriot Watt University, Edinburgh, United Kingdom Duration: 1 Sep 2014 → 3 Sep 2014 |
Publication series
Name | Proceedings (SemDial) |
---|---|
ISSN (Print) | 2308-2275 |
Workshop
Workshop | 18th Workshop on the Semantics and Pragmatics of Dialogue |
---|---|
Abbreviated title | SemDial 2014 |
Country | United Kingdom |
City | Edinburgh |
Period | 1/09/14 → 3/09/14 |