Deep Multi-Objective Reinforcement Learning for Utility-Based Infrastructural Maintenance Optimization

TL;DR

This paper presents MO-DCMAC, a multi-objective reinforcement learning method that optimizes infrastructural maintenance policies directly for multiple objectives, outperforming traditional rule-based approaches in diverse scenarios.

Contribution

Introduces MO-DCMAC, a novel multi-objective deep reinforcement learning algorithm for infrastructure maintenance, capable of handling non-linear utility functions and outperforming existing heuristic policies.

Findings

MO-DCMAC outperforms rule-based policies in multiple environments.

The method effectively optimizes for complex utility functions.

Performance validated on case studies including Amsterdam quay walls.

Abstract

In this paper, we introduce Multi-Objective Deep Centralized Multi-Agent Actor-Critic (MO- DCMAC), a multi-objective reinforcement learning (MORL) method for infrastructural maintenance optimization, an area traditionally dominated by single-objective reinforcement learning (RL) approaches. Previous single-objective RL methods combine multiple objectives, such as probability of collapse and cost, into a singular reward signal through reward-shaping. In contrast, MO-DCMAC can optimize a policy for multiple objectives directly, even when the utility function is non-linear. We evaluated MO-DCMAC using two utility functions, which use probability of collapse and cost as input. The first utility function is the Threshold utility, in which MO-DCMAC should minimize cost so that the probability of collapse is never above the threshold. The second is based on the Failure Mode, Effects, and Criticality Analysis (FMECA) methodology used by asset managers to asses maintenance plans. We evaluated MO-DCMAC, with both utility functions, in multiple maintenance environments, including ones based on a case study of the historical quay walls of Amsterdam. The performance of MO-DCMAC was compared against multiple rule-based policies based on heuristics currently used for constructing maintenance plans. Our results demonstrate that MO-DCMAC outperforms traditional rule-based policies across various environments and utility functions.