Multi-Agent Imitation Learning with Copulas
This addresses the challenge of capturing complex dependencies in multi-agent systems for applications like social or team-play scenarios, representing an incremental improvement over existing methods.
The paper tackled the problem of multi-agent imitation learning by explicitly modeling agent dependencies using copulas, resulting in a model that outperformed state-of-the-art baselines in action prediction tasks and generated trajectories close to expert demonstrations.
Multi-agent imitation learning aims to train multiple agents to perform tasks from demonstrations by learning a mapping between observations and actions, which is essential for understanding physical, social, and team-play systems. However, most existing works on modeling multi-agent interactions typically assume that agents make independent decisions based on their observations, ignoring the complex dependence among agents. In this paper, we propose to use copula, a powerful statistical tool for capturing dependence among random variables, to explicitly model the correlation and coordination in multi-agent systems. Our proposed model is able to separately learn marginals that capture the local behavioral patterns of each individual agent, as well as a copula function that solely and fully captures the dependence structure among agents. Extensive experiments on synthetic and real-world datasets show that our model outperforms state-of-the-art baselines across various scenarios in the action prediction task, and is able to generate new trajectories close to expert demonstrations.