The coordination between agents in multi-agent systems has become a popular topic in many fields. To catch the inner relationship between agents, the graph structure is combined with existing methods and improves the results. But in large-scale tasks with numerous agents, an overly complex graph would lead to a boost in computational cost and a decline in performance. Here we present DAGMIX, a novel graph-based value factorization method. Instead of a complete graph, DAGMIX generates a dynamic graph at each time step during training, on which it realizes a more interpretable and effective combining process through the attention mechanism. Experiments show that DAGMIX significantly outperforms previous SOTA methods in large-scale scenarios, as well as achieving promising results on other tasks.
This paper introduces an approach to enhance seismic fault recognition through self-supervised pretraining. Seismic fault interpretation holds great significance in the fields of geophysics and geology. However, conventional methods for seismic fault recognition encounter various issues, including dependence on data quality and quantity, as well as susceptibility to interpreter subjectivity. Currently, automated fault recognition methods proposed based on small synthetic datasets experience performance degradation when applied to actual seismic data. To address these challenges, we have introduced the concept of self-supervised learning, utilizing a substantial amount of relatively easily obtainable unlabeled seismic data for pretraining. Specifically, we have employed the Swin Transformer model as the core network and employed the SimMIM pretraining task to capture unique features related to discontinuities in seismic data. During the fine-tuning phase, inspired by edge detection techniques, we have also refined the structure of the Swin-UNETR model, enabling multiscale decoding and fusion for more effective fault detection. Experimental results demonstrate that our proposed method attains state-of-the-art performance on the Thebe dataset, as measured by the OIS and ODS metrics.
Few-shot medical image semantic segmentation is of paramount importance in the domain of medical image analysis. However, existing methodologies grapple with the challenge of data scarcity during the training phase, leading to over-fitting. To mitigate this issue, we introduce a novel Unsupervised Dense Few-shot Medical Image Segmentation Model Training Pipeline (DenseMP) that capitalizes on unsupervised dense pre-training. DenseMP is composed of two distinct stages: (1) segmentation-aware dense contrastive pre-training, and (2) few-shot-aware superpixel guided dense pre-training. These stages collaboratively yield a pre-trained initial model specifically designed for few-shot medical image segmentation, which can subsequently be fine-tuned on the target dataset. Our proposed pipeline significantly enhances the performance of the widely recognized few-shot segmentation model, PA-Net, achieving state-of-the-art results on the Abd-CT and Abd-MRI datasets. Code will be released after acceptance.
Value decomposition methods have gradually become popular in the cooperative multi-agent reinforcement learning field. However, almost all value decomposition methods follow the Individual Global Max (IGM) principle or its variants, which restricts the range of issues that value decomposition methods can resolve. Inspired by the notion of dual self-awareness in psychology, we propose a dual self-awareness value decomposition framework that entirely rejects the IGM premise. Each agent consists of an ego policy that carries out actions and an alter ego value function that takes part in credit assignment. The value function factorization can ignore the IGM assumption by using an explicit search procedure. We also suggest a novel anti-ego exploration mechanism to avoid the algorithm becoming stuck in a local optimum. As the first fully IGM-free value decomposition method, our proposed framework achieves desirable performance in various cooperative tasks.
Almost all multi-agent reinforcement learning algorithms without communication follow the principle of centralized training with decentralized execution. During centralized training, agents can be guided by the same signals, such as the global state. During decentralized execution, however, agents lack the shared signal. Inspired by viewpoint invariance and contrastive learning, we propose consensus learning for cooperative multi-agent reinforcement learning in this paper. Although based on local observations, different agents can infer the same consensus in discrete space. During decentralized execution, we feed the inferred consensus as an explicit input to the network of agents, thereby developing their spirit of cooperation. Our proposed method can be extended to various multi-agent reinforcement learning algorithms. Moreover, we carry out them on some fully cooperative tasks and get convincing results.