已经引入了平均野外游戏（MFG），以有效地近似战略代理人。最近，MFG中学习平衡的问题已经获得了动力，尤其是使用无模型增强学习（RL）方法。使用RL进一步扩展的一个限制因素是，解决MFG的现有算法需要混合近似数量的策略或$ Q $价值。在非线性函数近似的情况下，这远非微不足道的属性，例如，例如神经网络。我们建议解决这一缺点的两种方法。第一个从历史数据蒸馏到神经网络的混合策略，将其应用于虚拟游戏算法。第二种是基于正规化的在线混合方法，不需要记忆历史数据或以前的估计。它用于扩展在线镜下降。我们从数值上证明，这些方法有效地可以使用深RL算法来求解各种MFG。此外，我们表明这些方法的表现优于文献中的SOTA基准。

Semantic navigation is necessary to deploy mobile robots in uncontrolled environments like our homes, schools, and hospitals. Many learning-based approaches have been proposed in response to the lack of semantic understanding of the classical pipeline for spatial navigation, which builds a geometric map using depth sensors and plans to reach point goals. Broadly, end-to-end learning approaches reactively map sensor inputs to actions with deep neural networks, while modular learning approaches enrich the classical pipeline with learning-based semantic sensing and exploration. But learned visual navigation policies have predominantly been evaluated in simulation. How well do different classes of methods work on a robot? We present a large-scale empirical study of semantic visual navigation methods comparing representative methods from classical, modular, and end-to-end learning approaches across six homes with no prior experience, maps, or instrumentation. We find that modular learning works well in the real world, attaining a 90% success rate. In contrast, end-to-end learning does not, dropping from 77% simulation to 23% real-world success rate due to a large image domain gap between simulation and reality. For practitioners, we show that modular learning is a reliable approach to navigate to objects: modularity and abstraction in policy design enable Sim-to-Real transfer. For researchers, we identify two key issues that prevent today's simulators from being reliable evaluation benchmarks - (A) a large Sim-to-Real gap in images and (B) a disconnect between simulation and real-world error modes - and propose concrete steps forward.

Unsupervised representation learning aims at describing raw data efficiently to solve various downstream tasks. It has been approached with many techniques, such as manifold learning, diffusion maps, or more recently self-supervised learning. Those techniques are arguably all based on the underlying assumption that target functions, associated with future downstream tasks, have low variations in densely populated regions of the input space. Unveiling minimal variations as a guiding principle behind unsupervised representation learning paves the way to better practical guidelines for self-supervised learning algorithms.

自从最近的监督学习成功以来，应用数学和机器计算引起了很多希望。许多行业的从业人员一直在尝试从旧范式切换到机器学习。有趣的是，这些数据科学家比微调模型花费更多的时间取消，注释和清洁数据。该论文是由以下问题激发的：我们可以比监督学习的一个更通用的框架来从混乱数据中学习吗？假设数据收集的瓶颈在于注释。我们将弱的监督建模为给予而不是独特的目标，即一组目标候选者。我们认为，应该寻找与大多数观测值相匹配的``乐观''功能。这使我们能够得出一个原理来消除部分标签。我们还讨论了将无监督的学习技术纳入我们的框架的优势，特别是通过扩散技术接近的歧管正则化，为此我们得出了一种新算法，该算法通过输入维度比基线方法更好地扩展。最后，我们从被动转换为主动监督的学习，引入了``主动标签''框架，其中从业者可以查询有关所选数据的弱信息。除其他外，我们利用一个事实，即一个事实不需要全部信息来访问随机梯度并执行随机梯度下降。

The workhorse of machine learning is stochastic gradient descent. To access stochastic gradients, it is common to consider iteratively input/output pairs of a training dataset. Interestingly, it appears that one does not need full supervision to access stochastic gradients, which is the main motivation of this paper. After formalizing the "active labeling" problem, which focuses on active learning with partial supervision, we provide a streaming technique that provably minimizes the ratio of generalization error over the number of samples. We illustrate our technique in depth for robust regression.

由于数据的注释可以在大规模的实际问题中稀缺，利用未标记的示例是机器学习中最重要的方面之一。这是半监督学习的目的。从访问未标记数据的访问中受益，它很自然地弥漫将标记数据平稳地知识到未标记的数据。这诱导了Laplacian正规化的使用。然而，Laplacian正则化的当前实施遭受了几种缺点，特别是众所周知的维度诅咒。在本文中，我们提供了统计分析以克服这些问题，并揭示了具有所需行为的大型光谱滤波方法。它们通过（再现）内核方法来实现，我们提供了现实的计算指南，以使我们的方法可用于大量数据。