Learning Models of Adversarial Agent Behavior under Partial Observability
This work addresses the challenge of opponent modeling in real-world scenarios like sports and security, offering a domain-specific incremental improvement.
The paper tackles the problem of modeling adversarial agent behavior under partial observability by introducing GrAMMI, a graph neural network approach with mutual information maximization, which achieves a 31.68% higher average log-likelihood for future state predictions compared to baselines in pursuit-evasion domains.
The need for opponent modeling and tracking arises in several real-world scenarios, such as professional sports, video game design, and drug-trafficking interdiction. In this work, we present Graph based Adversarial Modeling with Mutal Information (GrAMMI) for modeling the behavior of an adversarial opponent agent. GrAMMI is a novel graph neural network (GNN) based approach that uses mutual information maximization as an auxiliary objective to predict the current and future states of an adversarial opponent with partial observability. To evaluate GrAMMI, we design two large-scale, pursuit-evasion domains inspired by real-world scenarios, where a team of heterogeneous agents is tasked with tracking and interdicting a single adversarial agent, and the adversarial agent must evade detection while achieving its own objectives. With the mutual information formulation, GrAMMI outperforms all baselines in both domains and achieves 31.68% higher log-likelihood on average for future adversarial state predictions across both domains.