TY - GEN
T1 - Dialogue policies for learning board games through multimodal communication
AU - Zare, Maryam
AU - Ayub, Ali
AU - Liu, Aishan
AU - Sudhakara, Sweekar
AU - Wagner, Alan
AU - Passonneau, Rebecca
N1 - Publisher Copyright:
© 2020 Association for Computational Linguistics.
PY - 2020
Y1 - 2020
N2 - 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.
AB - 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.
UR - http://www.scopus.com/inward/record.url?scp=85097204623&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85097204623&partnerID=8YFLogxK
U2 - 10.18653/v1/2020.sigdial-1.41
DO - 10.18653/v1/2020.sigdial-1.41
M3 - Conference contribution
AN - SCOPUS:85097204623
T3 - SIGDIAL 2020 - 21st Annual Meeting of the Special Interest Group on Discourse and Dialogue, Proceedings of the Conference
SP - 339
EP - 351
BT - SIGDIAL 2020 - 21st Annual Meeting of the Special Interest Group on Discourse and Dialogue, Proceedings of the Conference
PB - Association for Computational Linguistics (ACL)
T2 - 21st Annual Meeting of the Special Interest Group on Discourse and Dialogue, SIGDIAL 2020
Y2 - 1 July 2020 through 3 July 2020
ER -