Zhang Hong-Peng

Zhang Hong-Peng

Maneuver decision-making is the core of unmanned combat aerial vehicle for autonomous air combat. To solve this problem, we propose an automatic curriculum reinforcement learning method, which enables agents to learn effective decisions in air combat from scratch. The range of initial states are used for distinguishing curricula of different difficulty levels, thereby maneuver decision is divided into a series of sub-tasks from easy to difficult, and test results are used to change sub-tasks. As sub-tasks change, agents gradually learn to complete a series of sub-tasks from easy to difficult, enabling them to make effective maneuvering decisions to cope with various states without the need to spend effort designing reward functions. The ablation studied show that the automatic curriculum learning proposed in this article is an essential component for training through reinforcement learning, namely, agents cannot complete effective decisions without curriculum learning. Simulation experiments show that, after training, agents are able to make effective decisions given different states, including tracking, attacking and escaping, which are both rational and interpretable.

Zhang Hong-Peng

Maneuver decision-making can be regarded as a Markov decision process and can be address by reinforcement learning. However, original reinforcement learning algorithms can hardly solve the maneuvering decision-making problem. One reason is that agents use random actions in the early stages of training, which makes it difficult to get rewards and learn how to make effective decisions. To address this issue, a method based on proximal policy optimization and Monte Carlo tree search is proposed. The method uses proximal policy optimization to train the agent, and regards the results of air combat as targets to train the value network. Then, based on the value network and the visit count of each node, Monte Carlo tree search is used to find the actions with more expected returns than random actions, which can improve the training performance. The ablation studies and simulation experiments indicate that agents trained by the proposed method can make different decisions according to different states, which demonstrates that the method can solve the maneuvering decision problem that the original reinforcement learning algorithm cannot solve.