Deep reinforcement learning (DRL) integrates the feature representation ability of deep learning with the decision-making ability of reinforcement learning so that it can achieve powerful end-to-end learning control capabilities. In the past decade, DRL has made substantial advances in many tasks that require perceiving high-dimensional input and making optimal or near-optimal decisions. However, there are still many challenging problems in the theory and applications of DRL, especially in learning control tasks with limited samples, sparse rewards, and multiple agents. Researchers have proposed various solutions and new theories to solve these problems and promote the development of DRL. In addition, deep learning has stimulated the further development of many subfields of reinforcement learning, such as hierarchical reinforcement learning (HRL), multiagent reinforcement learning, and imitation learning. This article gives a comprehensive overview of the fundamental theories, key algorithms, and primary research domains of DRL. In addition to value-based and policy-based DRL algorithms, the advances in maximum entropy-based DRL are summarized. The future research topics of DRL are also analyzed and discussed.

The incomplete and imperfect essence of the battlefield situation results in a challenge to the efficiency, stability, and reliability of traditional intention recognition methods. For this problem, we propose a deep learning architecture that consists of a contrastive predictive coding (CPC) model, a variable-length long short-term memory network (LSTM) model, and an attention weight allocator for online intention recognition with incomplete information in wargame (W-CPCLSTM). First, based on the typical characteristics of intelligence data, a CPC model is designed to capture more global structures from limited battlefield information. Then, a variable-length LSTM model is employed to classify the learned representations into predefined intention categories. Next, a weighted approach to the training attention of CPC and LSTM is introduced to allow for the stability of the model. Finally, performance evaluation and application analysis of the proposed model for the online intention recognition task were carried out based on four different degrees of detection information and a perfect situation of ideal conditions in a wargame. Besides, we explored the effect of different lengths of intelligence data on recognition performance and gave application examples of the proposed model to a wargame platform. The simulation results demonstrate that our method not only contributes to the growth of recognition stability, but it also improves recognition accuracy by 7%-11%, 3%-7%, 3%-13%, and 3%-7%, the recognition speed by 6-32x, 4-18x, 13-*x, and 1-6x compared with the traditional LSTM, classical FCN, OctConv, and OctFCN models, respectively, which characterizes it as a promising reference tool for command decision-making.

Link prediction in networks has become a growing concern among researchers. In this paper, various link prediction methods are compared for better prediction results in intercity transportation networks. For practical consideration, a new index is proposed to sort the results of different algorithms taking both predicting precision and number of existing links into consideration. According to this index, we find the best threshold to determine the existence of links with simulate anneal. Experiments show that the index performs well in intercity transportation networks.

The successful application of deep reinforcement learning in RTS games such as StarCraft II has inspired people to apply multi-agent deep reinforcement learning(MADRL) to more fields. In the field of wargame, hexagonal maps are often used for simulation, which can't adapt to the rapid development of wargame. In continuous space of wargame, we construct a ship-defense scenario that includes multiple aircraft and ships. We apply deep Q network(DQN) method to MADRL, CNN to extract the features of multiple entities, and a centralized and distributed decision-making training architecture to control the aircraft's fixed-wing module components. Experiment results demonstrate the effectiveness of the proposed formulation, which show that the CNN-based feature extraction model can effectively defeat the built-in rule bot with multiple levels, and the training effect of CNN-based is better than the feature extraction method by full connection.