Reinforcement Learning-Based 3-D Sliding Mode Interception Guidance via Proximal Policy Optimization

This article proposes a novel 3-D sliding mode interception guidance law for maneuvering targets, which explores the potential of reinforcement learning (RL) techniques to enhance guidance accuracy and reduce chattering. The guidance problem of intercepting maneuvering targets is abstracted into a Markov decision process whose reward function is established to estimate the off-target amount and line-of-sight angular rate chattering. Importantly, a design framework of reward function suitable for general guidance problems based on RL can be proposed. Then, the proximal policy optimization algorithm with a satisfactory training performance is introduced to learn an action policy which represents the observed engagements states to sliding mode interception guidance. Finally, numerical simulations and comparisons are conducted to demonstrate the effectiveness of the proposed guidance law.