Interpretable Model-based Hierarchical Reinforcement Learning using Inductive Logic Programming
This addresses data-efficiency and interpretability issues in reinforcement learning, which is important for applications where environment interaction is costly and user trust is needed, though it appears incremental as it builds on existing symbolic RL and ILP approaches.
The paper tackles the lack of data-efficiency and interpretability in deep reinforcement learning by proposing a hierarchical framework using symbolic RL and inductive logic programming, achieving approximately 30-40% more data efficiency over previous methods.
Recently deep reinforcement learning has achieved tremendous success in wide ranges of applications. However, it notoriously lacks data-efficiency and interpretability. Data-efficiency is important as interacting with the environment is expensive. Further, interpretability can increase the transparency of the black-box-style deep RL models and hence gain trust from the users. In this work, we propose a new hierarchical framework via symbolic RL, leveraging a symbolic transition model to improve the data-efficiency and introduce the interpretability for learned policy. This framework consists of a high-level agent, a subtask solver and a symbolic transition model. Without assuming any prior knowledge on the state transition, we adopt inductive logic programming (ILP) to learn the rules of symbolic state transitions, introducing interpretability and making the learned behavior understandable to users. In empirical experiments, we confirmed that the proposed framework offers approximately between 30\% to 40\% more data efficiency over previous methods.