Zero-Shot Transferable Solution Method for Parametric Optimal Control Problems
This addresses the problem of high computational costs for real-time optimal control applications, though it is incremental as it builds on existing neural and imitation learning approaches.
The paper tackles the computational inefficiency of re-solving optimal control problems when objectives change by proposing a transferable method using function encoder policies, achieving near-optimal performance with minimal overhead in diverse numerical experiments.
This paper presents a transferable solution method for optimal control problems with varying objectives using function encoder (FE) policies. Traditional optimization-based approaches must be re-solved whenever objectives change, resulting in prohibitive computational costs for applications requiring frequent evaluation and adaptation. The proposed method learns a reusable set of neural basis functions that spans the control policy space, enabling efficient zero-shot adaptation to new tasks through either projection from data or direct mapping from problem specifications. The key idea is an offline-online decomposition: basis functions are learned once during offline imitation learning, while online adaptation requires only lightweight coefficient estimation. Numerical experiments across diverse dynamics, dimensions, and cost structures show our method delivers near-optimal performance with minimal overhead when generalizing across tasks, enabling semi-global feedback policies suitable for real-time deployment.