Figure 1: A five-fingered humanoid hand trained with reinforcement learning manipulating a block from an initial configuration to a goal configuration using vision for sensing.
translated by 谷歌翻译
Dealing with sparse rewards is one of the biggest challenges in Reinforcement Learning (RL). We present a novel technique called Hindsight Experience Replay which allows sample-efficient learning from rewards which are sparse and binary and therefore avoid the need for complicated reward engineering. It can be combined with an arbitrary off-policy RL algorithm and may be seen as a form of implicit curriculum. We demonstrate our approach on the task of manipulating objects with a robotic arm. In particular, we run experiments on three different tasks: pushing, sliding, and pick-and-place, in each case using only binary rewards indicating whether or not the task is completed. Our ablation studies show that Hindsight Experience Replay is a crucial ingredient which makes training possible in these challenging environments. We show that our policies trained on a physics simulation can be deployed on a physical robot and successfully complete the task. The video presenting our experiments is available at https://goo.gl/SMrQnI.
translated by 谷歌翻译
Bridging the 'reality gap' that separates simulated robotics from experiments on hardware could accelerate robotic research through improved data availability. This paper explores domain randomization, a simple technique for training models on simulated images that transfer to real images by randomizing rendering in the simulator. With enough variability in the simulator, the real world may appear to the model as just another variation. We focus on the task of object localization, which is a stepping stone to general robotic manipulation skills. We find that it is possible to train a real-world object detector that is accurate to 1.5 cm and robust to distractors and partial occlusions using only data from a simulator with non-realistic random textures. To demonstrate the capabilities of our detectors, we show they can be used to perform grasping in a cluttered environment. To our knowledge, this is the first successful transfer of a deep neural network trained only on simulated RGB images (without pre-training on real images) to the real world for the purpose of robotic control.
translated by 谷歌翻译
Machine learning has emerged recently as a powerful tool for predicting properties of quantum many-body systems. For many ground states of gapped Hamiltonians, generative models can learn from measurements of a single quantum state to reconstruct the state accurately enough to predict local observables. Alternatively, kernel methods can predict local observables by learning from measurements on different but related states. In this work, we combine the benefits of both approaches and propose the use of conditional generative models to simultaneously represent a family of states, by learning shared structures of different quantum states from measurements. The trained model allows us to predict arbitrary local properties of ground states, even for states not present in the training data, and without necessitating further training for new observables. We numerically validate our approach (with simulations of up to 45 qubits) for two quantum many-body problems, 2D random Heisenberg models and Rydberg atom systems.
translated by 谷歌翻译
Large language models (LLMs) have been shown to be able to perform new tasks based on a few demonstrations or natural language instructions. While these capabilities have led to widespread adoption, most LLMs are developed by resource-rich organizations and are frequently kept from the public. As a step towards democratizing this powerful technology, we present BLOOM, a 176B-parameter open-access language model designed and built thanks to a collaboration of hundreds of researchers. BLOOM is a decoder-only Transformer language model that was trained on the ROOTS corpus, a dataset comprising hundreds of sources in 46 natural and 13 programming languages (59 in total). We find that BLOOM achieves competitive performance on a wide variety of benchmarks, with stronger results after undergoing multitask prompted finetuning. To facilitate future research and applications using LLMs, we publicly release our models and code under the Responsible AI License.
translated by 谷歌翻译
数据是现代机器学习系统的命脉，包括音乐信息检索中的命脉（MIR）。但是，MIR长期以来一直被小型数据集和不可靠的标签所困扰。在这项工作中，我们建议使用生成建模打破这种瓶颈。通过使用室内合奏的结构化合成模型（在URMP上训练的MIDI-DDSP）的结构化合成模型，通过管道说明（在巴赫合唱上训练的椰子）模型，我们演示了一个能够生成无限量的逼真的合唱音乐的系统，其中包括丰富的结合音乐，包括混合，包括混合，，，包括混合，茎，MIDI，笔记级性能属性（Staccato，Vibrato等），甚至是细粒的合成参数（音高，振幅等）。我们称此系统为室内集合发生器（CEG），并使用它来生成来自四个不同腔室合奏（cocochorales）的大型合唱数据集。我们证明，使用我们的方法生成的数据改善了音乐转录和源分离的最新模型，并且我们均发布了系统和数据集作为MIR社区未来工作的开源基础。
translated by 谷歌翻译
机器学习潜力是分子模拟的重要工具，但是由于缺乏高质量数据集来训练它们的发展，它们的开发阻碍了它们。我们描述了Spice数据集，这是一种新的量子化学数据集，用于训练与模拟与蛋白质相互作用的药物样的小分子相关的潜在。它包含超过110万个小分子，二聚体，二肽和溶剂化氨基酸的构象。它包括15个元素，带电和未充电的分子以及广泛的共价和非共价相互作用。它提供了在{\ omega} b97m-d3（bj）/def2-tzVPPD理论水平以及其他有用的数量（例如多极矩和键阶）上计算出的力和能量。我们在其上训练一组机器学习潜力，并证明它们可以在化学空间的广泛区域中实现化学精度。它可以作为创建可转移的，准备使用潜在功能用于分子模拟的宝贵资源。
translated by 谷歌翻译
单词错误率（WER）是用于评估自动语音识别（ASR）模型质量的主要度量。已经表明，与典型的英语说话者相比，ASR模型的语音障碍者的扬声器往往更高。在如此高的错误率下，很难确定模型是否可以很有用。这项研究调查了BertScore的使用，BertScore是文本生成的评估指标，以提供对ASR模型质量和实用性的更有信息度量。将Bertscore和WER与语言病理学家手动注释以进行错误类型和评估手动注释的预测错误。发现Bertscore与人类的误差类型和评估评估更相关。在保留含义的拼字法变化（收缩和归一化误差）上，Bertscore特别强大。此外，使用顺序逻辑回归和Akaike的信息标准（AIC）测量，Bertscore比WER更好地评估了错误评估。总体而言，我们的发现表明，从实际角度评估ASR模型性能时，Bertscore可以补充，尤其是对于可访问性应用程序，即使模型的精度也比典型语音较低的模型也很有用。
translated by 谷歌翻译
研究过程自动化 - 对科学仪器，计算机，数据存储和其他资源的可靠，高效和可重复执行的可靠，高效和可重复执行，这是现代科学的基本要素。我们在此处报告Globus研究数据管理平台内的新服务，该服务可以将各种研究过程的规范作为可重复使用的动作集，流量以及在异质研究环境中执行此类流动的集合。为了以广泛的空间范围（例如，从科学仪器到远程数据中心）和时间范围（从几秒钟到几周），这些Globus自动化服务功能：1）云托管以可靠地执行长期持久的流量，尽管零星的失败，但这些Globus自动化服务功能：1） ; 2）声明性符号和可扩展的异步行动提供商API，用于定义和执行涉及任意资源的各种行动和流动规范； 3）授权授权机制，用于安全调用动作。这些服务允许研究人员将广泛的研究任务的管理外包和自动化为可靠，可扩展和安全的云平台。我们向Globus自动化服务提供用例
translated by 谷歌翻译
我们介绍了Gaudi，Gaudi是一种生成模型，能够捕获可以从移动的相机中沉浸式的复杂和现实3D场景的分布。我们通过一种可扩展而强大的方法解决了这个具有挑战性的问题，我们首先优化了散布辐射场和相机姿势的潜在表示。然后，该潜在表示将学习一个生成模型，该模型可以使3D场景的无条件生成和条件生成。我们的模型概括了以前的作品，该作品通过删除可以在样本中共享相机姿势分布的假设来关注单个对象。我们表明，高迪（Gaudi）在多个数据集的无条件生成设置中获得了最先进的性能，并允许有条件地生成3D场景给定的调理变量，例如稀疏图像观测值或描述场景的文本。
translated by 谷歌翻译