Learning Symbolic Rules for Interpretable Deep Reinforcement Learning
This addresses the problem of opaque decision-making in AI for users needing transparency, though it is incremental as it builds on existing DRL approaches.
The paper tackles the lack of interpretability in deep reinforcement learning by proposing a neural symbolic framework that integrates symbolic logic, resulting in improved interpretability with competitive performance compared to state-of-the-art methods.
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.