Group Effect Enhanced Generative Adversarial Imitation Learning for Individual Travel Behavior Modeling under Incentives

2025-09-08

AI Summary

Modeling individual travel behavior responses to incentive policies remains challenging due to sparse expert demonstrations, limited spatiotemporal coverage, and high behavioral diversity—leading to poor generalization in conventional MDP-based and imitation learning approaches. To address this, we propose a group-conditioned Generative Adversarial Imitation Learning (gcGAIL) framework. gcGAIL innovatively incorporates group-shared behavioral patterns as conditional inputs and integrates inverse reinforcement learning principles into the GAIL architecture via a behavior-clustering regularization mechanism. Evaluated on real-world bus fare discount interventions, gcGAIL significantly outperforms baseline methods—including GAIL and AIRL—in prediction accuracy, behavioral pattern representation efficiency, and long-term policy stability. Notably, it demonstrates superior robustness and generalization capability under low-data regimes and for underrepresented population subgroups.

Technology Category

• Machine Learning: Imitation Learning & Inverse Reinforcement Learning
• Humans and AI: Human-Aware Planning and Behavior Prediction
• Search and Optimization: Sampling/Simulation-based Search

Application Category

• Economics, Online Markets and Human Computation: Economic ramifications for generative AI infrastructure and applications
• User Modeling, Personalization and Recommendation: Metrics for user behavior and evaluating success
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions

Abstract

Understanding and modeling individual travel behavior responses is crucial for urban mobility regulation and policy evaluation. The Markov decision process (MDP) provides a structured framework for dynamic travel behavior modeling at the individual level. However, solving an MDP in this context is highly data-intensive and faces challenges of data quantity, spatial-temporal coverage, and situational diversity. To address these, we propose a group-effect-enhanced generative adversarial imitation learning (gcGAIL) model that improves the individual behavior modeling efficiency by leveraging shared behavioral patterns among passenger groups. We validate the gcGAIL model using a public transport fare-discount case study and compare against state-of-the-art benchmarks, including adversarial inverse reinforcement learning (AIRL), baseline GAIL, and conditional GAIL. Experimental results demonstrate that gcGAIL outperforms these methods in learning individual travel behavior responses to incentives over time in terms of accuracy, generalization, and pattern demonstration efficiency. Notably, gcGAIL is robust to spatial variation, data sparsity, and behavioral diversity, maintaining strong performance even with partial expert demonstrations and underrepresented passenger groups. The gcGAIL model predicts the individual behavior response at any time, providing the basis for personalized incentives to induce sustainable behavior changes (better timing of incentive injections).

Problem

• Modeling individual travel behavior responses to incentives
• Addressing data sparsity and diversity challenges in MDPs
• Improving accuracy and generalization in behavior prediction

Innovation

• Group-effect-enhanced GAIL model
• Leverages shared passenger group patterns
• Robust to spatial variation and sparsity