Preprint
Aug 2026
A Forward-Inverse Dynamic Game Framework for Enhanced Multi-Agent Trajectory Planning
A KL-regularized dynamic game with a state-dependent weight that adaptively balances optimality and behavioral priors is proposed for multi-agent trajectory planning in nonlinear dynamical systems with unknown agents'objectives and state-dependent inter-agent coupling.
Tianle Liu, Youcheng Niu, Jing Zeng et al.
· 0 citations