Preference-Agile Multi-Objective Optimization for Real-time Vehicle Dispatching

TL;DR

This paper introduces PAMOO, a dynamic multi-objective optimization method using deep reinforcement learning that allows real-time user preference adjustments for vehicle dispatching tasks.

Contribution

It proposes a novel DRL-based model enabling interactive preference adjustments in real-time multi-objective optimization for complex vehicle dispatching problems.

Findings

PAMOO outperforms two popular MOO methods in experiments.

The method demonstrates high generalization ability.

It effectively aligns user preferences with decision policies.

Abstract

Multi-objective optimization (MOO) has been widely studied in literature because of its versatility in human-centered decision making in real-life applications. Recently, demand for dynamic MOO is fast-emerging due to tough market dynamics that require real-time re-adjustments of priorities for different objectives. However, most existing studies focus either on deterministic MOO problems which are not practical, or non-sequential dynamic MOO decision problems that cannot deal with some real-life complexities. To address these challenges, a preference-agile multi-objective optimization (PAMOO) is proposed in this paper to permit users to dynamically adjust and interactively assign the preferences on the fly. To achieve this, a novel uniform model within a deep reinforcement learning (DRL) framework is proposed that can take as inputs users' dynamic preference vectors explicitly. Additionally, a calibration function is fitted to ensure high quality alignment between the preference vector inputs and the output DRL decision policy. Extensive experiments on challenging real-life vehicle dispatching problems at a container terminal showed that PAMOO obtains superior performance and generalization ability when compared with two most popular MOO methods. Our method presents the first dynamic MOO method for challenging \rev{dynamic sequential MOO decision problems