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

2024-06-10

arXiv.org

AI Summary

To address the multi-objective optimization challenge—balancing cost, safety, and service continuity—in urban infrastructure maintenance, this paper proposes a utility-driven deep multi-objective reinforcement learning (MORL) framework. Methodologically, it innovatively integrates utility theory into MORL by designing a Pareto-aware reward shaping mechanism and a hierarchical policy decomposition architecture; further, it employs graph neural networks for topology-aware state representation and combines Pareto-frontier guidance with Monte Carlo policy evaluation. Evaluated on benchmark simulations of bridge and water distribution networks, the framework reduces lifecycle maintenance costs by 18.7%, improves system reliability by 9.3%, and yields decision policies validated by engineering practice. Its transparent, interpretable policy logic significantly enhances practical applicability and domain adoption.

Technology Category

• Planning, Routing, and Scheduling: Optimization of Spatio-temporal Systems
• Search and Optimization: Learning to Search
• Reasoning under Uncertainty: Stochastic Optimization

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Economics, Online Markets and Human Computation: Incentives in network design for Web infrastructures and ecosystems

Problem

• Advanced Computer Learning Methods
• Infrastructure Maintenance
• Multi-Objective Optimization

Innovation

• Multi-Objective Deep Reinforcement Learning
• Infrastructure Maintenance Optimization
• MO-DCMAC