专为单药加固学习（RL）设计的算法通常无法在两人零和零和游戏中收敛到平衡。相反，在2P0S游戏中近似NASH和量子响应平衡（QRE）的游戏理论算法通常对RL竞争，并且很难扩展。结果，这两种情况的算法通常是分别开发和评估的。在这项工作中，我们表明，单个算法是一种近端正则化的镜像下降的简单扩展，我们称之为磁性镜下降（MMD） - 尽管它们的基本差异都可以在两种情况下产生强大的结果。从理论的角度来看，我们证明了MMD在广泛的游戏中线性收敛到QRE-这是第一阶求解器首次证明线性收敛。此外，我们通过自我播放作为表格NASH均衡求解器应用，我们从经验上表明，MMD在正常形式和广泛的形式游戏中都具有全反馈（这是标准RL算法首次完成），在正常形式和广泛的形式游戏中产生竞争性竞争因此）以及MMD在黑盒反馈设置中经验收敛。此外，对于单人Deep RL，在一小部分Atari和Mujoco游戏中，我们表明MMD可以与PPO的结果竞争。最后，对于多代理Deep RL，我们显示MMD可以在3x3突然的黑暗中胜过NFSP。

随机以外的（SEG）方法是解决各种机器学习任务中出现的最小最大优化和变分不等式问题（VIP）的最流行算法之一。然而，有关SEG的收敛性质的几个重要问题仍然是开放的，包括随机梯度的采样，迷你批量，用于单调有限和变分不等式的单调有限和变分别不等式，以及其他问题。为了解决这些问题，在本文中，我们开发了一种新颖的理论框架，使我们能够以统一的方式分析赛季的几种变体。除了标准设置之外，与均有界差异下的LipsChitzness和单调性或独立样本SEG相同 - 样本SEG，我们的方法可以分析之前从未明确考虑过的SEG的变体。值得注意的是，我们用任意抽样分析SEG，其中包括重要性采样和各种批量批量策略作为特殊情况。我们为SEG的新变种的率优于目前最先进的融合保证并依赖于更少的限制性假设。

我们调查随机镜面下降（SMD）的趋同相对光滑和平滑凸优化。在相对平滑的凸优化中，我们为SMD提供了新的收敛保证，并持续步骤。对于平滑的凸优化，我们提出了一种新的自适应步骤方案 - 镜子随机Polyak Spectize（MSP）。值得注意的是，我们的收敛导致两个设置都不会使有界渐变假设或有界方差假设，并且我们向邻域显示在插值下消失的邻居的融合。MSP概括了最近提出的随机Polyak Spectize（SPS）（Loizou等，2021）以镜子血液镜子，并且在继承镜子血清的好处的同时，现代机器学习应用仍然是实用和高效的。我们将我们的结果与各种监督的学习任务和SMD的不同实例相结合，展示了MSP的有效性。

用于解决无约束光滑游戏的两个最突出的算法是经典随机梯度下降 - 上升（SGDA）和最近引入的随机共识优化（SCO）[Mescheder等，2017]。已知SGDA可以收敛到特定类别的游戏的静止点，但是当前的收敛分析需要有界方差假设。 SCO用于解决大规模对抗问题，但其收敛保证仅限于其确定性变体。在这项工作中，我们介绍了预期的共同胁迫条件，解释了它的好处，并在这种情况下提供了SGDA和SCO的第一次迭代收敛保证，以解决可能是非单调的一类随机变分不等式问题。我们将两种方法的线性会聚到解决方案的邻域时，当它们使用恒定的步长时，我们提出了富有识别的步骤化切换规则，以保证对确切解决方案的融合。此外，我们的收敛保证在任意抽样范式下担保，因此，我们对迷你匹配的复杂性进行了解。

我们研究了随机双线性最小利益的优化问题，呈现了恒定步长的相同样本随机以（SEG）方法的分析，并呈现了产生有利收敛的方法的变化。在锐度对比度与基本的SEG方法相比，其最后迭代仅对纳什均衡的固定邻域，SEG以相同的标准设置在相同的标准设置下可被提供给NASH均衡的迭代，并且通过结合预定，进一步提高了这种速率重新启动程序。在插值环境中，噪声在纳什均衡消失时，我们达到了最佳的常量收敛速度。我们展示了验证我们理论发现的数值实验，并在配备迭代平均和重启时证明SEG方法的有效性。

This article formulates a generic representation of a path-following controller operating under contained motion, which was developed in the context of surgical robotics. It reports two types of constrained motion: i) Bilateral Constrained Motion, also called Remote Center Motion (RCM), and ii) Unilaterally Constrained Motion (UCM). In the first case, the incision hole has almost the same diameter as the robotic tool. In contrast, in the second state, the diameter of the incision orifice is larger than the tool diameter. The second case offers more space where the surgical instrument moves freely without constraints before touching the incision wall. The proposed method combines two tasks that must operate hierarchically: i) respect the RCM or UCM constraints formulated by equality or inequality, respectively, and ii) perform a surgical assignment, e.g., scanning or ablation expressed as a 3D path-following task. The proposed methods and materials were tested first on our simulator that mimics realistic conditions of middle ear surgery, and then on an experimental platform. Different validation scenarios were carried out experimentally to assess quantitatively and qualitatively each developed approach. Although ultimate precision was not the goal of this work, our concept is validated with enough accuracy (inferior to 100 micrometres) for ear surgery.

Several self-supervised representation learning methods have been proposed for reinforcement learning (RL) with rich observations. For real-world applications of RL, recovering underlying latent states is crucial, particularly when sensory inputs contain irrelevant and exogenous information. In this work, we study how information bottlenecks can be used to construct latent states efficiently in the presence of task-irrelevant information. We propose architectures that utilize variational and discrete information bottlenecks, coined as RepDIB, to learn structured factorized representations. Exploiting the expressiveness bought by factorized representations, we introduce a simple, yet effective, bottleneck that can be integrated with any existing self-supervised objective for RL. We demonstrate this across several online and offline RL benchmarks, along with a real robot arm task, where we find that compressed representations with RepDIB can lead to strong performance improvements, as the learned bottlenecks help predict only the relevant state while ignoring irrelevant information.

To face the dependency on fossil fuels and limit carbon emissions, fuel cells are a very promising technology and appear to be a key candidate to tackle the increase of the energy demand and promote the energy transition. To meet future needs for both transport and stationary applications, the time to market of fuel cell stacks must be drastically reduced. Here, a new concept to shorten their development time by introducing a disruptive and highefficiency data augmentation approach based on artificial intelligence is presented. Our results allow reducing the testing time before introducing a product on the market from a thousand to a few hours. The innovative concept proposed here can support engineering and research tasks during the fuel cell development process to achieve decreased development costs alongside a reduced time to market.

A learned system uses machine learning (ML) internally to improve performance. We can expect such systems to be vulnerable to some adversarial-ML attacks. Often, the learned component is shared between mutually-distrusting users or processes, much like microarchitectural resources such as caches, potentially giving rise to highly-realistic attacker models. However, compared to attacks on other ML-based systems, attackers face a level of indirection as they cannot interact directly with the learned model. Additionally, the difference between the attack surface of learned and non-learned versions of the same system is often subtle. These factors obfuscate the de-facto risks that the incorporation of ML carries. We analyze the root causes of potentially-increased attack surface in learned systems and develop a framework for identifying vulnerabilities that stem from the use of ML. We apply our framework to a broad set of learned systems under active development. To empirically validate the many vulnerabilities surfaced by our framework, we choose 3 of them and implement and evaluate exploits against prominent learned-system instances. We show that the use of ML caused leakage of past queries in a database, enabled a poisoning attack that causes exponential memory blowup in an index structure and crashes it in seconds, and enabled index users to snoop on each others' key distributions by timing queries over their own keys. We find that adversarial ML is a universal threat against learned systems, point to open research gaps in our understanding of learned-systems security, and conclude by discussing mitigations, while noting that data leakage is inherent in systems whose learned component is shared between multiple parties.

In intensively managed forests in Europe, where forests are divided into stands of small size and may show heterogeneity within stands, a high spatial resolution (10 - 20 meters) is arguably needed to capture the differences in canopy height. In this work, we developed a deep learning model based on multi-stream remote sensing measurements to create a high-resolution canopy height map over the "Landes de Gascogne" forest in France, a large maritime pine plantation of 13,000 km$^2$ with flat terrain and intensive management. This area is characterized by even-aged and mono-specific stands, of a typical length of a few hundred meters, harvested every 35 to 50 years. Our deep learning U-Net model uses multi-band images from Sentinel-1 and Sentinel-2 with composite time averages as input to predict tree height derived from GEDI waveforms. The evaluation is performed with external validation data from forest inventory plots and a stereo 3D reconstruction model based on Skysat imagery available at specific locations. We trained seven different U-net models based on a combination of Sentinel-1 and Sentinel-2 bands to evaluate the importance of each instrument in the dominant height retrieval. The model outputs allow us to generate a 10 m resolution canopy height map of the whole "Landes de Gascogne" forest area for 2020 with a mean absolute error of 2.02 m on the Test dataset. The best predictions were obtained using all available satellite layers from Sentinel-1 and Sentinel-2 but using only one satellite source also provided good predictions. For all validation datasets in coniferous forests, our model showed better metrics than previous canopy height models available in the same region.