Deakin University

File(s) under permanent embargo

A multi-objective deep reinforcement learning framework

journal contribution
posted on 2022-11-18, 02:37 authored by Thanh Thi NguyenThanh Thi Nguyen, Duy Nguyen, P Vamplew, Saeid Nahavandi, Richard DazeleyRichard Dazeley, Chee Peng LimChee Peng Lim
This paper introduces a new scalable multi-objective deep reinforcement learning (MODRL) framework based on deep Q-networks. We develop a high-performance MODRL framework that supports both single-policy and multi-policy strategies, as well as both linear and non-linear approaches to action selection. The experimental results on two benchmark problems (two-objective deep sea treasure environment and three-objective Mountain Car problem) indicate that the proposed framework is able to find the Pareto-optimal solutions effectively. The proposed framework is generic and highly modularized, which allows the integration of different deep reinforcement learning algorithms in different complex problem domains. This therefore overcomes many disadvantages involved with standard multi-objective reinforcement learning methods in the current literature. The proposed framework acts as a testbed platform that accelerates the development of MODRL for solving increasingly complicated multi-objective problems.



Engineering Applications of Artificial Intelligence





Publication classification

C1 Refereed article in a scholarly journal