Multi-Agent Reinforcement Learning for Intraday Operating Rooms Scheduling under Uncertainty

TL;DR

This paper introduces a multi-agent reinforcement learning framework for real-time intraday operating room scheduling under uncertainty, outperforming heuristics and providing interpretable policies.

Contribution

It formulates OR scheduling as a cooperative Markov game and develops a MARL approach with centralized training and decentralized execution, incorporating rich system states and conflict-free scheduling.

Findings

Learned policy outperforms rule-based heuristics across multiple metrics

Policy prioritizes emergencies and batches similar cases to reduce setups

Quantifies optimality gaps relative to an ex post MIP oracle

Abstract

Intraday surgical scheduling is a multi-objective decision problem under uncertainty-balancing elective throughput, urgent and emergency demand, delays, sequence-dependent setups, and overtime. We formulate the problem as a cooperative Markov game and propose a multi-agent reinforcement learning (MARL) framework in which each operating room (OR) is an agent trained with centralized training and decentralized execution. All agents share a policy trained via Proximal Policy Optimization (PPO), which maps rich system states to actions, while a within-epoch sequential assignment protocol constructs conflict-free joint schedules across ORs. A mixed-integer pre-schedule provides reference starting times for electives; we impose type-specific quadratic delay penalties relative to these references and a terminal overtime penalty, yielding a single reward that captures throughput, timeliness, and staff workload. In simulations reflecting a realistic hospital mix (six ORs, eight surgery types, random urgent and emergency arrivals), the learned policy outperforms six rule-based heuristics across seven metrics and three evaluation subsets, and, relative to an ex post MIP oracle, quantifies optimality gaps. Policy analytics reveal interpretable behavior-prioritizing emergencies, batching similar cases to reduce setups, and deferring lower-value electives. We also derive a suboptimality bound for the sequential decomposition under simplifying assumptions. We discuss limitations-including OR homogeneity and the omission of explicit staffing constraints-and outline extensions. Overall, the approach offers a practical, interpretable, and tunable data-driven complement to optimization for real-time OR scheduling.