[3Yin2] Interactive session 1

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

〇Daiki Kimura¹, Subhajit Chaudhury¹, Sarathkrishna Swaminathan¹, Tsunehiko Tanaka^1,2, 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.