Despite advancements in language-controlled reinforcement learning (LC-RL) for basic domains and straightforward commands (e.g., object manipulation and navigation), effectively extending LC-RL to comprehend and execute high-level or abstract instructions in complex, multi-agent environments, such as football games, remains a significant challenge. To address this gap, we introduce Language-Controlled Diverse Style Policies (LCDSP), a novel LC-RL paradigm specifically designed for complex scenarios. LCDSP comprises two key components: a Diverse Style Training (DST) method and a Style Interpreter (SI). The DST method efficiently trains a single policy capable of exhibiting a wide range of diverse behaviors by modulating agent actions through style parameters (SP). The SI is designed to accurately and rapidly translate high-level language instructions into these corresponding SP. Through extensive experiments in a complex 5v5 football environment, we demonstrate that LCDSP effectively comprehends abstract tactical instructions and accurately executes the desired diverse behavioral styles, showcasing its potential for complex, real-world applications.

Symbolic regression (SR) has emerged as a pivotal technique for uncovering the intrinsic information within data and enhancing the interpretability of AI models. However, current state-of-the-art (sota) SR methods struggle to perform correct recovery of symbolic expressions from high-noise data. To address this issue, we introduce a novel noise-resilient SR (NRSR) method capable of recovering expressions from high-noise data. Our method leverages a novel reinforcement learning (RL) approach in conjunction with a designed noise-resilient gating module (NGM) to learn symbolic selection policies. The gating module can dynamically filter the meaningless information from high-noise data, thereby demonstrating a high noise-resilient capability for the SR process. And we also design a mixed path entropy (MPE) bonus term in the RL process to increase the exploration capabilities of the policy. Experimental results demonstrate that our method significantly outperforms several popular baselines on benchmarks with high-noise data. Furthermore, our method also can achieve sota performance on benchmarks with clean data, showcasing its robustness and efficacy in SR tasks.

Acromegaly, a chronic endocrine disorder, requires early diagnosis to prevent severe complications. Existing deep learning-based diagnostic methods often prioritize accuracy at the expense of computational complexity and feature diversity, limiting their deployment in resource-constrained IoT environments. This paper proposes Mobile Hybrid Mamba (MHMamba), a lightweight model for edge-based acromegaly screening that synergistically integrates Inverted Residual Attention Convolution (IRAC) and VMamba. The design leverages the hierarchical local feature extraction of convolutional networks in IRAC to effectively capture fine-grained pathological patterns, while incorporating VMamba’s selective state-space mechanism for linear-complexity global modeling of anatomical dependencies. This complementary fusion enables comprehensive representation learning of both localized manifestations and structural correlations in medical images. Consequently, MHMamba achieves state-of-the-art performance (2.8–3.1% improvement in precision, recall, and F1-score) while maintaining ultra-lightweight parameters (13.882M) and low computational overhead (2.054G FLOPs). Crucially, MHMamba’s mobile-friendly architecture enables real-time facial analysis on smartphones, making it suitable for IoT-driven telemedicine and decentralized health monitoring. Through occlusion experiments and GradCAM++ visualization, we identify key facial regions (nose, mouth, and cheekbones) critical for diagnosis, aligning with clinical biomarkers. The model’s interpretability and portability position it as a pivotal tool for IoT-enabled smart healthcare systems, bridging the gap between AI-driven diagnostics and edge device deployment.

Deep reinforcement learning (DRL) has emerged as a leading technique for designing AI-bots in the gaming industry. However, practical implementation of DRL-trained bots often encounter two significant challenges: improving strength and diversifying strategies to satisfy player expectations. We observe that the strength of AI-bots are intrinsically tied to the diversity of emerged strategies. Considering this relationship, we introduce diversity is strength (DIS), a novel DRL training framework capable of concurrently training multiple types of AI-bots for adversarial games. These bots are interconnected through an elaborated history model pool (HMP) structure, thereby improving their strength and strategy diversity to tackle the aforementioned challenges. We further devise a model evaluation and sampling scheme to form the HMP, identify superior models, and enrich the model strategies. The DIS can generate diverse and reliable strategies without the need for human data. This method is validated by achieving first-place finishes in two AI competitions based on complex adversarial games, including Google Research Football and Olympic Games. Experiments demonstrate that bots trained using DIS attain an excellent performance and plentiful strategies. Specifically, diversity analysis demonstrates that the trained bots possess a wealth of strategies, and ablation studies confirm the beneficial impact of the designed modules on the training process.

Automatic sleep staging methods usually extract hand-crafted features or network trained features from signals recorded by polysomnography (PSG), and then estimate the stages by various classifiers. In this study, we propose a classification approach based on a hierarchical neural network to process multi-channel PSG signals for improving the performance of automatic five-class sleep staging. The proposed hierarchical network contains two stages: comprehensive feature learning stage and sequence learning stage. The first stage is used to obtain the feature matrix by fusing the hand-crafted features and network trained features. A multi-flow recurrent neural network (RNN) as the second stage is utilized to fully learn temporal information between sleep epochs and fine-tune the parameters in the first stage. The proposed model was evaluated by 147 full night recordings in a public sleep database, the Montreal Archive of Sleep Studies (MASS). The proposed approach can achieve the overall accuracy of 0.878, and the F1-score is 0.818. The results show that the approach can achieve better performance compared to the state-of-the-art methods. Ablation experiment and model analysis proved the effectiveness of different components of the proposed model. The proposed approach allows automatic sleep stage classification by multi-channel PSG signals with different criteria standards, signal characteristics, and epoch divisions, and it has the potential to exploit sleep information comprehensively.