Multi-agent deep reinforcement learning with centralized training and decentralized execution for transportation infrastructure management
This addresses the problem of scalable and optimal maintenance planning for transportation infrastructure managers, though it appears incremental as it builds on existing multi-agent DRL and CTDE approaches.
The paper tackles the computationally intensive problem of life-cycle management for large transportation infrastructure systems by developing a multi-agent deep reinforcement learning framework with centralized training and decentralized execution (DDMAC-CTDE). The result shows that the method vastly outperforms traditional management policies, providing near-optimal solutions under real-world constraints in a realistic example application in Virginia, USA.
We present a multi-agent Deep Reinforcement Learning (DRL) framework for managing large transportation infrastructure systems over their life-cycle. Life-cycle management of such engineering systems is a computationally intensive task, requiring appropriate sequential inspection and maintenance decisions able to reduce long-term risks and costs, while dealing with different uncertainties and constraints that lie in high-dimensional spaces. To date, static age- or condition-based maintenance methods and risk-based or periodic inspection plans have mostly addressed this class of optimization problems. However, optimality, scalability, and uncertainty limitations are often manifested under such approaches. The optimization problem in this work is cast in the framework of constrained Partially Observable Markov Decision Processes (POMDPs), which provides a comprehensive mathematical basis for stochastic sequential decision settings with observation uncertainties, risk considerations, and limited resources. To address significantly large state and action spaces, a Deep Decentralized Multi-agent Actor-Critic (DDMAC) DRL method with Centralized Training and Decentralized Execution (CTDE), termed as DDMAC-CTDE is developed. The performance strengths of the DDMAC-CTDE method are demonstrated in a generally representative and realistic example application of an existing transportation network in Virginia, USA. The network includes several bridge and pavement components with nonstationary degradation, agency-imposed constraints, and traffic delay and risk considerations. Compared to traditional management policies for transportation networks, the proposed DDMAC-CTDE method vastly outperforms its counterparts. Overall, the proposed algorithmic framework provides near optimal solutions for transportation infrastructure management under real-world constraints and complexities.