Learning Symbolic Rules for Interpretable Deep Reinforcement Learning
Abstract
Recent progress in deep reinforcement learning (DRL) can be largely attributed to the use of neural networks. However, this black-box approach fails to explain the learned policy in a human understandable way. To address this challenge and improve the transparency, we propose a Neural Symbolic Reinforcement Learning framework by introducing symbolic logic into DRL. This framework features a fertilization of reasoning and learning modules, enabling end-to-end learning with prior symbolic knowledge. Moreover, interpretability is achieved by extracting the logical rules learned by the reasoning module in a symbolic rule space. The experimental results show that our framework has better interpretability, along with competing performance in comparison to state-of-the-art approaches.
Cite
@article{arxiv.2103.08228,
title = {Learning Symbolic Rules for Interpretable Deep Reinforcement Learning},
author = {Zhihao Ma and Yuzheng Zhuang and Paul Weng and Hankz Hankui Zhuo and Dong Li and Wulong Liu and Jianye Hao},
journal= {arXiv preprint arXiv:2103.08228},
year = {2021}
}