深度强化学习（DRL）是一种仅从演示和经验中学习机器人控制政策的有前途的方法。为了涵盖机器人的整个动态行为，DRL训练是通常在仿真环境中得出的主动探索过程。尽管这种模拟培训廉价且快速，但将DRL算法应用于现实世界的设置很困难。如果对代理进行训练直到它们在模拟中安全执行，则由于模拟动力学和物理机器人之间的差异引起的SIM到真实差距，将其传输到物理系统很困难。在本文中，我们提出了一种在线培训DRL代理的方法，可以使用基于模型的安全主管在实体车辆上自动驾驶。我们的解决方案使用监督系统检查代理选择的操作是安全还是不安全，并确保在车辆上始终采取安全措施。这样，我们可以在安全，快速，有效地训练DRL算法的同时绕过SIM到现实的问题。我们提供各种现实世界实验，在线培训一辆小型实体车辆，可以自动驾驶，没有事先模拟培训。评估结果表明，我们的方法在未崩溃的同时提高了样品效率的训练代理，并且受过训练的代理比在模拟中训练的代理表现出更好的驾驶性能。

语言模型既展示了定量的改进，又展示了新的定性功能，随着规模的增加。尽管它们具有潜在的变革性影响，但这些新能力的特征却很差。为了为未来的研究提供信息，为破坏性的新模型能力做准备，并改善社会有害的效果，至关重要的是，我们必须了解目前和近乎未来的能力和语言模型的局限性。为了应对这一挑战，我们介绍了超越模仿游戏基准（Big Bench）。 Big Bench目前由204个任务组成，由132家机构的442位作者贡献。任务主题是多样的，从语言学，儿童发展，数学，常识性推理，生物学，物理学，社会偏见，软件开发等等。 Big-Bench专注于被认为超出当前语言模型的功能的任务。我们评估了OpenAI的GPT型号，Google内部密集变压器体系结构和大型基础上的开关稀疏变压器的行为，跨越了数百万到数十亿个参数。此外，一个人类专家评估者团队执行了所有任务，以提供强大的基准。研究结果包括：模型性能和校准都随规模改善，但绝对的术语（以及与评估者的性能相比）；在模型类中的性能非常相似，尽管带有稀疏性。逐渐和预测的任务通常涉及大量知识或记忆成分，而在临界规模上表现出“突破性”行为的任务通常涉及多个步骤或组成部分或脆性指标；社交偏见通常会随着含糊不清的环境而随着规模而增加，但这可以通过提示来改善。

本文介绍了第一个致力于2020挑战的结果和分析，重点是开发语音技术的匿名解决方案。我们提供了对提交的系统和评估结果的分析，提供了挑战设计的系统概述。特别是，我们描述了用于系统开发和评估的语音匿名任务和数据集。此外，我们呈现不同的攻击模型和相关目标和主观评估指标。我们介绍了两个匿名化的基线，并提供了由挑战参与者开发的匿名化系统的摘要描述。我们向基线和提交的系统报告客观和主观评估结果。此外，我们提出了作为评估后分析的一部分开发的替代隐私度量和攻击模型的实验结果。最后，我们总结了我们的见解和观察，这将影响下一个语音普遍挑战版的设计和未来语音匿名化研究的某些方向。

The recent increase in public and academic interest in preserving biodiversity has led to the growth of the field of conservation technology. This field involves designing and constructing tools that utilize technology to aid in the conservation of wildlife. In this article, we will use case studies to demonstrate the importance of designing conservation tools with human-wildlife interaction in mind and provide a framework for creating successful tools. These case studies include a range of complexities, from simple cat collars to machine learning and game theory methodologies. Our goal is to introduce and inform current and future researchers in the field of conservation technology and provide references for educating the next generation of conservation technologists. Conservation technology not only has the potential to benefit biodiversity but also has broader impacts on fields such as sustainability and environmental protection. By using innovative technologies to address conservation challenges, we can find more effective and efficient solutions to protect and preserve our planet's resources.

We address the problem of extracting key steps from unlabeled procedural videos, motivated by the potential of Augmented Reality (AR) headsets to revolutionize job training and performance. We decompose the problem into two steps: representation learning and key steps extraction. We employ self-supervised representation learning via a training strategy that adapts off-the-shelf video features using a temporal module. Training implements self-supervised learning losses involving multiple cues such as appearance, motion and pose trajectories extracted from videos to learn generalizable representations. Our method extracts key steps via a tunable algorithm that clusters the representations extracted from procedural videos. We quantitatively evaluate our approach with key step localization and also demonstrate the effectiveness of the extracted representations on related downstream tasks like phase classification. Qualitative results demonstrate that the extracted key steps are meaningful to succinctly represent the procedural tasks.

We introduce Argoverse 2 (AV2) - a collection of three datasets for perception and forecasting research in the self-driving domain. The annotated Sensor Dataset contains 1,000 sequences of multimodal data, encompassing high-resolution imagery from seven ring cameras, and two stereo cameras in addition to lidar point clouds, and 6-DOF map-aligned pose. Sequences contain 3D cuboid annotations for 26 object categories, all of which are sufficiently-sampled to support training and evaluation of 3D perception models. The Lidar Dataset contains 20,000 sequences of unlabeled lidar point clouds and map-aligned pose. This dataset is the largest ever collection of lidar sensor data and supports self-supervised learning and the emerging task of point cloud forecasting. Finally, the Motion Forecasting Dataset contains 250,000 scenarios mined for interesting and challenging interactions between the autonomous vehicle and other actors in each local scene. Models are tasked with the prediction of future motion for "scored actors" in each scenario and are provided with track histories that capture object location, heading, velocity, and category. In all three datasets, each scenario contains its own HD Map with 3D lane and crosswalk geometry - sourced from data captured in six distinct cities. We believe these datasets will support new and existing machine learning research problems in ways that existing datasets do not. All datasets are released under the CC BY-NC-SA 4.0 license.

In training neural networks, batch normalization has many benefits, not all of them entirely understood. But it also has some drawbacks. Foremost is arguably memory consumption, as computing the batch statistics requires all instances within the batch to be processed simultaneously, whereas without batch normalization it would be possible to process them one by one while accumulating the weight gradients. Another drawback is that that distribution parameters (mean and standard deviation) are unlike all other model parameters in that they are not trained using gradient descent but require special treatment, complicating implementation. In this paper, I show a simple and straightforward way to address these issues. The idea, in short, is to add terms to the loss that, for each activation, cause the minimization of the negative log likelihood of a Gaussian distribution that is used to normalize the activation. Among other benefits, this will hopefully contribute to the democratization of AI research by means of lowering the hardware requirements for training larger models.

In this paper, we introduce neural texture learning for 6D object pose estimation from synthetic data and a few unlabelled real images. Our major contribution is a novel learning scheme which removes the drawbacks of previous works, namely the strong dependency on co-modalities or additional refinement. These have been previously necessary to provide training signals for convergence. We formulate such a scheme as two sub-optimisation problems on texture learning and pose learning. We separately learn to predict realistic texture of objects from real image collections and learn pose estimation from pixel-perfect synthetic data. Combining these two capabilities allows then to synthesise photorealistic novel views to supervise the pose estimator with accurate geometry. To alleviate pose noise and segmentation imperfection present during the texture learning phase, we propose a surfel-based adversarial training loss together with texture regularisation from synthetic data. We demonstrate that the proposed approach significantly outperforms the recent state-of-the-art methods without ground-truth pose annotations and demonstrates substantial generalisation improvements towards unseen scenes. Remarkably, our scheme improves the adopted pose estimators substantially even when initialised with much inferior performance.

Prevailing methods for assessing and comparing generative AIs incentivize responses that serve a hypothetical representative individual. Evaluating models in these terms presumes homogeneous preferences across the population and engenders selection of agglomerative AIs, which fail to represent the diverse range of interests across individuals. We propose an alternative evaluation method that instead prioritizes inclusive AIs, which provably retain the requisite knowledge not only for subsequent response customization to particular segments of the population but also for utility-maximizing decisions.

We designed and constructed an A-sized base autonomous underwater vehicle (AUV), augmented with a stack of modular and extendable hardware and software, including autonomy, navigation, control and high fidelity simulation capabilities (A-size stands for the standard sonobuoy form factor, with a maximum diameter of 124 mm). Subsequently, we extended this base vehicle with a novel tuna-inspired morphing fin payload module (referred to as the Morpheus AUV), to achieve good directional stability and exceptional maneuverability; properties that are highly desirable for rigid hull AUVs, but are presently difficult to achieve because they impose contradictory requirements. The morphing fin payload allows the base AUV to dynamically change its stability-maneuverability qualities by using morphing fins, which can be deployed, deflected and retracted, as needed. The base vehicle and Morpheus AUV were both extensively field tested in-water in the Charles river, Massachusetts, USA; by conducting hundreds of hours of operations over a period of two years. The maneuvering capability of the Morpheus AUV was evaluated with and without the use of morphing fins to quantify the performance improvement. The Morpheus AUV was able to showcase an exceptional turning rate of around 25-35 deg/s. A maximum turn rate improvement of around 35% - 50% was gained through the use of morphing fins.