Imitation learning (IL) is a simple and powerful way to use high-quality human driving data, which can be collected at scale, to identify driving preferences and produce human-like behavior. However, policies based on imitation learning alone often fail to sufficiently account for safety and reliability concerns. In this paper, we show how imitation learning combined with reinforcement learning using simple rewards can substantially improve the safety and reliability of driving policies over those learned from imitation alone. In particular, we use a combination of imitation and reinforcement learning to train a policy on over 100k miles of urban driving data, and measure its effectiveness in test scenarios grouped by different levels of collision risk. To our knowledge, this is the first application of a combined imitation and reinforcement learning approach in autonomous driving that utilizes large amounts of real-world human driving data.

Microprocessor architects are increasingly resorting to domain-specific customization in the quest for high-performance and energy-efficiency. As the systems grow in complexity, fine-tuning architectural parameters across multiple sub-systems (e.g., datapath, memory blocks in different hierarchies, interconnects, compiler optimization, etc.) quickly results in a combinatorial explosion of design space. This makes domain-specific customization an extremely challenging task. Prior work explores using reinforcement learning (RL) and other optimization methods to automatically explore the large design space. However, these methods have traditionally relied on single-agent RL/ML formulations. It is unclear how scalable single-agent formulations are as we increase the complexity of the design space (e.g., full stack System-on-Chip design). Therefore, we propose an alternative formulation that leverages Multi-Agent RL (MARL) to tackle this problem. The key idea behind using MARL is an observation that parameters across different sub-systems are more or less independent, thus allowing a decentralized role assigned to each agent. We test this hypothesis by designing domain-specific DRAM memory controller for several workload traces. Our evaluation shows that the MARL formulation consistently outperforms single-agent RL baselines such as Proximal Policy Optimization and Soft Actor-Critic over different target objectives such as low power and latency. To this end, this work opens the pathway for new and promising research in MARL solutions for hardware architecture search.

深入学习的强化学习（RL）的结合导致了一系列令人印象深刻的壮举，许多相信（深）RL提供了一般能力的代理。然而，RL代理商的成功往往对培训过程中的设计选择非常敏感，这可能需要繁琐和易于易于的手动调整。这使得利用RL对新问题充满挑战，同时也限制了其全部潜力。在许多其他机器学习领域，AutomL已经示出了可以自动化这样的设计选择，并且在应用于RL时也会产生有希望的初始结果。然而，自动化强化学习（AutorL）不仅涉及Automl的标准应用，而且还包括RL独特的额外挑战，其自然地产生了不同的方法。因此，Autorl已成为RL中的一个重要研究领域，提供来自RNA设计的各种应用中的承诺，以便玩游戏等游戏。鉴于RL中考虑的方法和环境的多样性，在不同的子领域进行了大部分研究，从Meta学习到进化。在这项调查中，我们寻求统一自动的领域，我们提供常见的分类法，详细讨论每个区域并对研究人员来说是一个兴趣的开放问题。

部分观察到的马尔可夫决策过程（POMDP）是一种强大的框架，用于捕获涉及状态和转换不确定性的决策问题。然而，大多数目前的POMDP规划者不能有效地处理它们经常在现实世界中遇到的非常高的观测（例如，机器人域中的图像观察）。在这项工作中，我们提出了视觉树搜索（VTS），一个学习和规划过程，将生成模型与基于在线模型的POMDP规划的脱机中学到的。 VTS通过利用一组深入生成观测模型来预测和评估蒙特卡罗树搜索计划员的图像观测的可能性，乘坐脱机模型培训和在线规划。我们展示VTS对不同观察噪声的强大稳健，因为它利用在线，基于模型的规划，可以适应不同的奖励结构，而无需重新列车。这种新方法优于基线最先进的策略计划算法，同时使用显着降低的离线培训时间。

我们研究了在室内路线上捕获的360度图像中的自动生成导航指令。现有的发电机遭受较差的视觉接地，导致它们依赖语言前沿和幻觉对象。我们的Marky-MT5系统通过专注于视觉地标来解决这一点;它包括第一阶段地标检测器和第二级发生器 - 多峰，多语言，多任务编码器 - 解码器。要培训它，我们在房间顶部（RXR）数据集的顶部引导地标注释。使用文本解析器，来自RXR的姿势迹线的弱监督，以及在1.8B图像上培训的多语言图像文本编码器，我们识别1.1M英语，印地语和泰卢语的地标描述并将其接地为Panoramas的特定区域。在房间到室内，人类途径在Marky-MT5的指示之后获得了71％的成功率（SR），只害羞他们的75％SR在人类指令之后 - 以及与其他发电机的SR高于SRS。对RXR更长的评估，不同的路径上的三种语言获得61-64％的SRS。在新颖环境中生成这种高质量的导航指令是迈向对话导航工具的一步，可以促进对指令跟随代理的大规模培训。

我们为自主无人驾驶飞行器（UAV）设计了一个瓶颈分析工具。该工具通过利用自主UV中的各种组件之间的基本关系，如传感器，计算，身体动态。为了保证安全操作，同时最大化UAV的性能（例如，速度），必须精心设计（或选择）的计算，传感器和其他机械性能。我们所提出的工具的目标是提供一种可视化模型，帮助系统架构师了解自主无人机的最佳计算设计（或选择）。该工具可在此处提供：〜\ url {https://bit.ly/skyline-tool}

我们通过在计算图的空间中搜索计算基于值的无模型RL代理以优化的计算函数来提出一种用于元学习增强学习算法的方法。学到的算法是域 - 不可思议的，可以推广到训练期间未见的新环境。我们的方法既可以从头开始学习，又可以从已知的现有算法（例如DQN）学习，从而实现可解释的修改，从而改善性能。从头开始学习简单的经典控制和网格世界任务，我们的方法重新发现了时间差异（TD）算法。我们从DQN进行了引导，我们重点介绍了两种学到的算法，这些算法比其他经典控制任务，GridWorld类型任务和Atari游戏获得了良好的概括性能。对学习算法行为的分析表明，与最近提出的RL算法相似，该算法解决了基于价值的方法的高估。

深度加强学习已经实现了重要的里程碑，然而，加强学习培训和推理的计算需求仍然很大。量化是减少神经网络的计算开销的有效方法，但在加强学习的背景下，尚不清楚量化的计算益处是否超过了相应量化误差引入的精度成本。为了量化这一权衡，我们对加强学习的量化进行了广泛的研究。我们应用标准量化技术，如训练后量化（PTQ）和量化意识培训（QAT），以全面的加强学习任务（Atari，Gym），算法（A2C，DDPG，DQN，D4PG，PPO）和模型（MLPS，CNNS）并表明可以将策略量化为8位，而不会降低奖励，从而在资源受限的边缘设备上实现了显着的推论加速。通过标准量化技术对加固学习政策的有效性，我们介绍了一种新颖的量化算法，\ TEXTIT {ACTORQ}，用于量化演员 - 学习者分布式增强学习培训。通过利用Learner上的全精度优化并在演员上的量化执行，\ Textit {ActorQ}在保持收敛时启用8位推理。我们开发了一个用于围绕\ Texit {Actorq}的量化强化学习培训系统，并展示结束于最终加速$> $ 1.5 $ \ times $ - 2.5 $ \ times $超过一系列任务的完整精度培训（深型控制套件） 。最后，我们分解了分布式强化学习培训（如通信时间，推理时间，模型加载时间等）的各种运行时成本，并评估量化对这些系统属性的影响。

The outbreak of the SARS-CoV-2 pandemic has put healthcare systems worldwide to their limits, resulting in increased waiting time for diagnosis and required medical assistance. With chest radiographs (CXR) being one of the most common COVID-19 diagnosis methods, many artificial intelligence tools for image-based COVID-19 detection have been developed, often trained on a small number of images from COVID-19-positive patients. Thus, the need for high-quality and well-annotated CXR image databases increased. This paper introduces POLCOVID dataset, containing chest X-ray (CXR) images of patients with COVID-19 or other-type pneumonia, and healthy individuals gathered from 15 Polish hospitals. The original radiographs are accompanied by the preprocessed images limited to the lung area and the corresponding lung masks obtained with the segmentation model. Moreover, the manually created lung masks are provided for a part of POLCOVID dataset and the other four publicly available CXR image collections. POLCOVID dataset can help in pneumonia or COVID-19 diagnosis, while the set of matched images and lung masks may serve for the development of lung segmentation solutions.

In the era of big astronomical surveys, our ability to leverage artificial intelligence algorithms simultaneously for multiple datasets will open new avenues for scientific discovery. Unfortunately, simply training a deep neural network on images from one data domain often leads to very poor performance on any other dataset. Here we develop a Universal Domain Adaptation method DeepAstroUDA, capable of performing semi-supervised domain alignment that can be applied to datasets with different types of class overlap. Extra classes can be present in any of the two datasets, and the method can even be used in the presence of unknown classes. For the first time, we demonstrate the successful use of domain adaptation on two very different observational datasets (from SDSS and DECaLS). We show that our method is capable of bridging the gap between two astronomical surveys, and also performs well for anomaly detection and clustering of unknown data in the unlabeled dataset. We apply our model to two examples of galaxy morphology classification tasks with anomaly detection: 1) classifying spiral and elliptical galaxies with detection of merging galaxies (three classes including one unknown anomaly class); 2) a more granular problem where the classes describe more detailed morphological properties of galaxies, with the detection of gravitational lenses (ten classes including one unknown anomaly class).