Imitation Learning of Correlated Policies in Stackelberg Games
This addresses the challenge of learning correlated policies in asymmetric multi-agent systems like economics and security, though it appears incremental as it builds on existing MAIL methods.
The paper tackles the problem of accurately modeling interdependent agent behaviors in Stackelberg games, where traditional multi-agent imitation learning methods fail due to asymmetric decision-making, by proposing a correlated policy occupancy measure and the Latent Stackelberg Differential Network (LSDN), which better reproduces complex interaction dynamics in experiments on Iterative Matrix Games and multi-agent particle environments.
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 scalability challenges, particularly in high-dimensional environments, and suffer from unstable training. To address these challenges, we propose a correlated policy occupancy measure specifically designed for Stackelberg games and introduce the Latent Stackelberg Differential Network (LSDN) to match it. LSDN models two-agent interactions as shared latent state trajectories and uses multi-output Geometric Brownian Motion (MO-GBM) to effectively capture joint policies. By leveraging MO-GBM, LSDN disentangles environmental influences from agent-driven transitions in latent space, enabling the simultaneous learning of interdependent policies. This design eliminates the need for adversarial training and simplifies the learning process. Extensive experiments on Iterative Matrix Games and multi-agent particle environments demonstrate that LSDN can better reproduce complex interaction dynamics than existing MAIL methods.