Bayesian inference of self-intention attributed by observer

Yosuke Fukuchi, Masahiko Osawa, Hiroshi Yamakawa, Tatsuji Takahashi, Michita Imai

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

Abstract

Most of agents that learn policy for tasks with reinforcement learning (RL) lack the ability to communicate with people, which makes human-agent collaboration challenging. We believe that, in order for RL agents to comprehend utterances from human colleagues, RL agents must infer the mental states that people attribute to them because people sometimes infer an interlocutor’s mental states and communicate on the basis of this mental inference. This paper proposes PublicSelf model, which is a model of a person who infers how the person’s own behavior appears to their colleagues. We implemented the PublicSelf model for an RL agent in a simulated environment and examined the inference of the model by comparing it with people’s judgment. The results showed that the agent’s intention that people attributed to the agent’s movement was correctly inferred by the model in scenes where people could find certain intentionality from the agent’s behavior.

Original languageEnglish
Title of host publicationHAI 2018 - Proceedings of the 6th International Conference on Human-Agent Interaction
PublisherAssociation for Computing Machinery, Inc
Pages3-10
Number of pages8
ISBN (Electronic)9781450359535
DOIs
Publication statusPublished - 2018 Dec 4
Event6th International Conference on Human-Agent Interaction, HAI 2018 - Southampton, United Kingdom
Duration: 2018 Dec 152018 Dec 18

Publication series

NameHAI 2018 - Proceedings of the 6th International Conference on Human-Agent Interaction

Other

Other6th International Conference on Human-Agent Interaction, HAI 2018
CountryUnited Kingdom
CitySouthampton
Period18/12/1518/12/18

Keywords

  • Bayesian inference
  • Human-agent interaction
  • Public self-awareness
  • PublicSelf model
  • Reinforcement learning
  • Theory of mind

ASJC Scopus subject areas

  • Human-Computer Interaction
  • Artificial Intelligence
  • Software

Fingerprint Dive into the research topics of 'Bayesian inference of self-intention attributed by observer'. Together they form a unique fingerprint.

  • Cite this

    Fukuchi, Y., Osawa, M., Yamakawa, H., Takahashi, T., & Imai, M. (2018). Bayesian inference of self-intention attributed by observer. In HAI 2018 - Proceedings of the 6th International Conference on Human-Agent Interaction (pp. 3-10). (HAI 2018 - Proceedings of the 6th International Conference on Human-Agent Interaction). Association for Computing Machinery, Inc. https://doi.org/10.1145/3284432.3284438