Grounding Strategic Conversation: Using Negotiation Dialogues to Predict Trades in a Win-Lose Game

作者: Anais Cadilhac , Alex Lascarides , Farah Benamara , Nicholas Asher

DOI:

关键词:

摘要: This paper describes a method that predicts which trades players execute during winlose game. Our uses data collected from chat negotiations of the game The Settlers Catan and exploits conversation to construct dynamically partial model each player’s preferences. in turn yields equilibrium trading moves via principles theory. We compare our against four baselines show tracking how preferences evolve through dialogue reasoning about are both crucial success.

参考文章(29)
Elise Bonzon, Modélisation des interactions entre agents rationnels : les jeux booléens Université Paul Sabatier - Toulouse III. ,(2007)
Frederik Schadd, Sander Bakkes, Pieter Spronck, Opponent Modeling in Real-Time Strategy Games. GAMEON. pp. 61- 70 ,(2007)
Nicholas Asher, Elise Bonzon, Alex Lascarides, Extracting and Modelling Preferences from Dialogue Computational Intelligence for Knowledge-Based Systems Design. pp. 542- 553 ,(2010) , 10.1007/978-3-642-14049-5_56
Faisal M. Khan, Tianhao Wu, Todd A. Fisher, William M. Pottenger, Lori A. Shuler, Posting Act Tagging Using Transformation-Based Learning. Foundations of Data Mining and knowledge Discovery. pp. 319- 331 ,(2005)
Giuseppe Carenini, Shafiq Joty, Chin-Yew Lin, Unsupervised modeling of dialog acts in asynchronous conversations international joint conference on artificial intelligence. pp. 1807- 1813 ,(2011) , 10.5591/978-1-57735-516-8/IJCAI11-303
Laure Vieu, Anaïs Cadilhac, Stergos Afantenos, Oliver Lemon, Alex Lascarides, Farah Benamara, Simon Keizer, Pascal Denis, Verena Rieser, Saumya Paul, Markus Guhe, Nicholas Asher, Cédric Dégremont, Philippe Muller, Developing a corpus of strategic conversation in The Settlers of Catan SeineDial 2012 - The 16th WORKSHOP ON THE SEMANTICS AND PRAGMATICS OF DIALOGUE. ,(2012)
Christopher Amato, Guy Shani, High-level reinforcement learning in strategy games adaptive agents and multi-agents systems. pp. 75- 82 ,(2010) , 10.5555/1838206.1838217