A multi-objective deep reinforcement learning framework

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.

Authors

• Thanh Thi Nguyen
• Ngoc Duy Nguyen
• Peter Vamplew Federation University
• Saeid Nahavandi
• Richard Dazeley Deakin University
• Chee Peng Lim

Keywords

• Reinforcement learning
• Multi-objective
• Deep learning
• Single-policy
• Multi-policy