Deep CFR enables end-to-end approximation of Nash equilibria in imperfect-information games(IIGs) but is sensitive to hyperparameters, making manual tuning inefficient. To address this, we propose PT-DCFR, which integrates Population-Based Training(PBT) with Deep CFR to dynamically optimize hyperparameters during training. Building upon this, we further introduce P2T-DCFR, which decouples parameter selection from model performance.

With the rapid advancement of remote sensing technology, numerous deep learning-based object detection and recognition models have emerged. However, in military target detection tasks, there may be an imbalance in the quantities of different target categories, leading to suboptimal detection performance for minority classes during both training and evaluation. Simultaneously, small target images, often characterized by lower resolutions, are prone to information loss during the propagation and fusion processes in neural networks, resulting in misclassification as background or similar objects. In this paper, we propose a novel model called HIRSA for aerial aircraft target recognition based on YOLOv5, which integrates the Convolutional Block Attention Module (CBAM) and a new module called Res2Net to address the data imbalances and weak feature representation associated with small target images. Our extensive experimental results and analysis demonstrate that HIRSA successfully enhances the model's capability to detect and rocognize military aircraft targets, particularly those belonging to underrepresented categories and with small image size.

Counterfactual regret minimization (CFR) is a popular method for finding approximate Nash equilibrium in two-player zero-sum games with imperfect information. Solving large-scale games with CFR needs a combination of abstraction techniques and certain expert knowledge, which constrains its scalability. Recent neural-based CFR methods mitigate the need for abstraction and expert knowledge by training an efficient network to directly obtain counterfactual regret without abstraction. However, these methods only consider estimating regret values for individual actions, neglecting the evaluation of state values, which are significant for decision-making. In this article, we introduce deep dueling CFR (D2CFR), which emphasizes the state value estimation by employing a novel value network with a dueling structure. Moreover, a rectification module based on a time-shifted Monte Carlo simulation is designed to rectify the inaccurate state value estimation. Extensive experimental results are conducted to show that D2CFR converges faster and outperforms comparison methods on test games.

While the artificial intelligence theory for solving the perfect-information games has been well developed in recent years, great challenges are still posed in dealing with the imperfect-information game due to the huge state space and hidden information involved in it. In this paper, we design an online strategy solving framework for six-player no-limit Texas hold'em poker. Based on hand isomorphism and hand strength evalution, the framework provides an efficient situation estimation method for six-player poker. Such method could greatly reduce the the state space in six-player poker as well as effectively evaluate the current hands. The poker agent based on our method won the third place in the 2018 AAAI-ACPC.