Knowledge-Based Sequential Decision-Making Under Uncertainty

TL;DR

This paper introduces a novel method combining deep reinforcement learning with symbolic planning to improve data-efficiency and explainability in hierarchical decision-making, validated by experiments on benchmark tasks.

Contribution

It presents a new algorithm integrating DRL with symbolic planning, enhancing subtask explainability and data-efficiency over existing methods.

Findings

Outperforms state-of-the-art in data-efficiency

Improves explainability of subtasks

Validated on benchmark datasets

Abstract

Deep reinforcement learning (DRL) algorithms have achieved great success on sequential decision-making problems, yet is criticized for the lack of data-efficiency and explainability. Especially, explainability of subtasks is critical in hierarchical decision-making since it enhances the transparency of black-box-style DRL methods and helps the RL practitioners to understand the high-level behavior of the system better. To improve the data-efficiency and explainability of DRL, declarative knowledge is introduced in this work and a novel algorithm is proposed by integrating DRL with symbolic planning. Experimental analysis on publicly available benchmarks validates the explainability of the subtasks and shows that our method can outperform the state-of-the-art approach in terms of data-efficiency.