[4E1-OS-11a] 人間と共生する対話知能(1/4)

[4E1-OS-11a-01] The Use of Action-Relation Probability in Policy Reuse for Dialog Management

Tung The Nguyen³, 〇Koichiro Yoshino^1,2,3, Sakriani Sakti^3,2, Satoshi Nakamura^3,2 (1. Robotics Project (GRP), Institute of Physical and Chemical Research (RIKEN), 2. Center for Advanced Intelligence Project (AIP), Institute of Physical and Chemical Research (RIKEN), 3. Nara Institute of Science and Technology)

Keywords:dialogue systems, dialogue management, reinforcement learning

Reusing policies in a new domain, which is trained on the existing domain, is an important problem of dialogue management research based on reinforcement learning. This work defines action-relation probabilities between the action spaces of the new and the target domains using mixture density networks for the reuse of policies. Experimental results showed that the proposed modeling of action-relation probabilities based on component matching using regression realized the effective policy reuse.