Dialogue policies for learning board games through multimodal communication

Maryam Zare, Ali Ayub, Aishan Liu, Sweekar Sudhakara, Alan Wagner, Rebecca Passonneau

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

2 Scopus citations

Abstract

This paper presents MDP policy learning for agents to learn strategic behavior-how to play board games-during multimodal dialogues. Policies are trained offline in simulation, with dialogues carried out in a formal language. The agent has a temporary belief state for the dialogue, and a persistent knowledge store represented as an extensive-form game tree. How well the agent learns a new game from a dialogue with a simulated partner is evaluated by how well it plays the game, given its dialoguefinal knowledge state. During policy training, we control for the simulated dialogue partner's level of informativeness in responding to questions. The agent learns best when its trained policy matches the current dialogue partner's informativeness. We also present a novel data collection for training natural language modules. Human subjects who engaged in dialogues with a baseline system rated the system's language skills as above average. Further, results confirm that human dialogue partners also vary in their informativeness.

Original languageEnglish (US)
Title of host publicationSIGDIAL 2020 - 21st Annual Meeting of the Special Interest Group on Discourse and Dialogue, Proceedings of the Conference
PublisherAssociation for Computational Linguistics (ACL)
Pages339-351
Number of pages13
ISBN (Electronic)9781952148026
DOIs
StatePublished - 2020
Event21st Annual Meeting of the Special Interest Group on Discourse and Dialogue, SIGDIAL 2020 - Virtual, Online
Duration: Jul 1 2020Jul 3 2020

Publication series

NameSIGDIAL 2020 - 21st Annual Meeting of the Special Interest Group on Discourse and Dialogue, Proceedings of the Conference

Conference

Conference21st Annual Meeting of the Special Interest Group on Discourse and Dialogue, SIGDIAL 2020
CityVirtual, Online
Period7/1/207/3/20

All Science Journal Classification (ASJC) codes

  • Computer Vision and Pattern Recognition
  • Modeling and Simulation
  • Computer Graphics and Computer-Aided Design
  • Human-Computer Interaction

Fingerprint

Dive into the research topics of 'Dialogue policies for learning board games through multimodal communication'. Together they form a unique fingerprint.

Cite this