Optimizing Constrained Guidance Policy With Minimum Overload Regularization

Weilin Luo, Jinhu Lu

Abstract

Using reinforcement learning (RL) algorithm to optimize guidance law can address non-idealities in complex environment. However, the optimization is difficult due to huge state-action space, unstable training, and high requirements on expertise. In this paper, the constrained guidance policy of a neural guidance system is optimized using improved RL algorithm, which is motivated by the idea of traditional model-based guidance method. A novel optimization objective with minimum overload regularization is developed to restrain the guidance policy directly from generating redundant missile maneuver. Moreover, a bi-level curriculum learning is designed to facilitate the policy optimization. Experiment results show that the proposed minimum overload regularization can reduce the vertical overloads of missile significantly, and the bi-level curriculum learning can further accelerate the optimization of guidance policy.
BibTeX
@article{luo2022optimizing,
  author = {Weilin Luo and Jinhu Lu},
  title = {{Optimizing Constrained Guidance Policy With Minimum Overload Regularization}},
  journal = {IEEE Trans. Circuits Syst. i Regul. pap},
  year = {2022},
  doi = {10.1109/tcsi.2022.3163463},
}

Loading related content...

Figure