Neural Logic Reinforcement Learning

Luo, S ORCID: 0000-0003-4760-0372 and Jiang, Zhengyao
(2019) Neural Logic Reinforcement Learning. In: The Thirty-sixth International Conference on Machine Learning, 2019-06-10 - 2019-06-15, Long Beach Convention Center, Long Beach..

[img] Text
NLRL_paper.pdf - Accepted Version

Download (321kB) | Preview


Deep reinforcement learning (DRL) has achieved significant breakthroughs in various tasks. However, most DRL algorithms suffer a problem of generalising the learned policy, which makes the policy performance largely affected even by minor modifications of the training environment. Except that, the use of deep neural networks makes the learned policies hard to be interpretable. To address these two challenges, we propose a novel algorithm named Neural Logic Reinforcement Learning (NLRL) to represent the policies in reinforcement learning by first-order logic. NLRL is based on policy gradient methods and differentiable inductive logic programming that have demonstrated significant advantages in terms of interpretability and generalisability in supervised tasks. Extensive experiments conducted on cliff-walking and blocks manipulation tasks demonstrate that NLRL can induce interpretable policies achieving near-optimal performance while showing good generalisability to environments of different initial states and problem sizes.

Item Type: Conference or Workshop Item (Unspecified)
Depositing User: Symplectic Admin
Date Deposited: 07 Jun 2019 10:15
Last Modified: 04 Sep 2022 07:14
Related URLs: