Competitive Multi-Operator Reinforcement Learning for Joint Pricing and Fleet Rebalancing in AMoD Systems

2026-03-05

AI Summary

This study addresses the challenge of jointly optimizing pricing and fleet rebalancing strategies in a competitive autonomous mobility-on-demand (AMoD) market with multiple operators. It introduces, for the first time, a multi-operator competition framework that integrates multi-agent reinforcement learning, discrete choice models, and game theory to endogenously capture passenger demand allocation and strategic interactions among operators. Simulation experiments based on real-world urban data demonstrate that, compared to a monopolistic setting, the competitive equilibrium yields lower prices and markedly different fleet deployment patterns. The proposed method effectively converges to equilibrium and exhibits robustness against partially unobservable competitor strategies, thereby revealing the fundamental impact of market competition on operational decision-making in AMoD systems.

Technology Category

• Multiagent Systems: Mechanism Design
• Search and Optimization: Learning to Search
• Game Theory and Economic Paradigms: Mechanism Design

Application Category

• Economics, Online Markets and Human Computation: The sharing economy
• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

Autonomous Mobility-on-Demand (AMoD) systems promise to revolutionize urban transportation by providing affordable on-demand services to meet growing travel demand. However, realistic AMoD markets will be competitive, with multiple operators competing for passengers through strategic pricing and fleet deployment. While reinforcement learning has shown promise in optimizing single-operator AMoD control, existing work fails to capture competitive market dynamics. We investigate the impact of competition on policy learning by introducing a multi-operator reinforcement learning framework where two operators simultaneously learn pricing and fleet rebalancing policies. By integrating discrete choice theory, we enable passenger allocation and demand competition to emerge endogenously from utility-maximizing decisions. Experiments using real-world data from multiple cities demonstrate that competition fundamentally alters learned behaviors, leading to lower prices and distinct fleet positioning patterns compared to monopolistic settings. Notably, we demonstrate that learning-based approaches are robust to the additional stochasticity of competition, with competitive agents successfully converging to effective policies while accounting for partially unobserved competitor strategies.

Problem

• Autonomous Mobility-on-Demand
• multi-operator competition
• pricing
• fleet rebalancing
• reinforcement learning

Innovation

• Multi-Operator Reinforcement Learning
• Competitive AMoD
• Joint Pricing and Rebalancing
• Discrete Choice Theory
• Endogenous Demand Competition