JSAI2022

Presentation information

Interactive Session

General Session » Interactive Session

[3Yin2] Interactive session 1

Thu. Jun 16, 2022 11:30 AM - 1:10 PM Room Y (Event Hall)

[3Yin2-56] Reinforcement Learning by Neuro-Symbolic AI

〇Daiki Kimura1, Subhajit Chaudhury1, Sarathkrishna Swaminathan1, Tsunehiko Tanaka1,2, Don Joven Agravante1, Michiaki Tatsubori1, Asim Munawar1, Alexander Gray1 (1.IBM Research, 2.Waseda University)

Keywords:Neuro-Symbolic, Reinforcement Learning, Text-based Game

Reinforcement learning often require many trials for obtaining an optimal policy, and no interpretability for trained policies is provided. To overcome these problems, we propose a novel reinforcement learning method by neuro-symbolic AI which is a combination of recent deep neural network and symbolic reasoning. Our experimental results show training with the proposed method converges significantly faster than other state-of-the-art neuro-only and neuro-symbolic methods in a text-based game benchmark.

Authentication for paper PDF access

A password is required to view paper PDFs. If you are a registered participant, please log on the site from Participant Log In.
You could view the PDF with entering the PDF viewing password bellow.

Password