Imitation Learning Of Correlated Policies In Stackelberg Games

Abstract

Stackelberg games, widely applied in domains like economics and security, involve asymmetric interactions where a leader's strategy drives follower responses. Accurately modeling these dynamics allows domain experts to optimize strategies in interactive scenarios, such as turn-based sports like badminton. In multi-agent systems, agent behaviors are interdependent, and traditional Multi-Agent Imitation Learning (MAIL) methods often fail to capture these complex interactions. Correlated policies, which account for opponents' strategies, are essential for accurately modeling such dynamics. However, even methods designed for learning correlated policies, like CoDAIL, struggle in Stackelberg games due to their asymmetric decision-making, where leaders and followers cannot simultaneously account for each other's actions, often leading to non-correlated policies. Furthermore, existing MAIL methods that match occupancy measures or use adversarial techniques like GAIL or Inverse RL face scalabi

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keywang2025imitation

Related papers

• Multi-agent Interactions Modeling With Correlated Policies (2020)2.60
• Stackelberg Games For Learning Emergent Behaviors During Competitive Autocurricula (2023)5.84
• Model-free Reinforcement Learning For Stochastic Stackelberg Security Games (2020)5.24
• Interactive Inverse Reinforcement Learning For Cooperative Games (2021)0.00
• Sample-efficient Learning Of Stackelberg Equilibria In General-sum Games (2021)0.00
• Multi-agent Reinforcement Learning In Bayesian Stackelberg Markov Games For Adaptive Moving Target Defense (2020)0.00
• Oracles & Followers: Stackelberg Equilibria In Deep Multi-agent Reinforcement Learning (2022)0.00
• Inducing Stackelberg Equilibrium Through Spatio-temporal Sequential Decision-making In Multi-agent Reinforcement Learning (2023)7.50