Sunquakes are seismic emissions visible on the solar surface, associated with some solar flares. Although discovered in 1998, they have only recently become a more commonly detected phenomenon. Despite the availability of several manual detection guidelines, to our knowledge, the astrophysical data produced for sunquakes is new to the field of Machine Learning. Detecting sunquakes is a daunting task for human operators and this work aims to ease and, if possible, to improve their detection. Thus, we introduce a dataset constructed from acoustic egression-power maps of solar active regions obtained for Solar Cycles 23 and 24 using the holography method. We then present a pedagogical approach to the application of machine learning representation methods for sunquake detection using AutoEncoders, Contrastive Learning, Object Detection and recurrent techniques, which we enhance by introducing several custom domain-specific data augmentation transformations. We address the main challenges of the automated sunquake detection task, namely the very high noise patterns in and outside the active region shadow and the extreme class imbalance given by the limited number of frames that present sunquake signatures. With our trained models, we find temporal and spatial locations of peculiar acoustic emission and qualitatively associate them to eruptive and high energy emission. While noting that these models are still in a prototype stage and there is much room for improvement in metrics and bias levels, we hypothesize that their agreement on example use cases has the potential to enable detection of weak solar acoustic manifestations.

Humans have internal models of robots (like their physical capabilities), the world (like what will happen next), and their tasks (like a preferred goal). However, human internal models are not always perfect: for example, it is easy to underestimate a robot's inertia. Nevertheless, these models change and improve over time as humans gather more experience. Interestingly, robot actions influence what this experience is, and therefore influence how people's internal models change. In this work we take a step towards enabling robots to understand the influence they have, leverage it to better assist people, and help human models more quickly align with reality. Our key idea is to model the human's learning as a nonlinear dynamical system which evolves the human's internal model given new observations. We formulate a novel optimization problem to infer the human's learning dynamics from demonstrations that naturally exhibit human learning. We then formalize how robots can influence human learning by embedding the human's learning dynamics model into the robot planning problem. Although our formulations provide concrete problem statements, they are intractable to solve in full generality. We contribute an approximation that sacrifices the complexity of the human internal models we can represent, but enables robots to learn the nonlinear dynamics of these internal models. We evaluate our inference and planning methods in a suite of simulated environments and an in-person user study, where a 7DOF robotic arm teaches participants to be better teleoperators. While influencing human learning remains an open problem, our results demonstrate that this influence is possible and can be helpful in real human-robot interaction.

When robots learn reward functions using high capacity models that take raw state directly as input, they need to both learn a representation for what matters in the task -- the task ``features" -- as well as how to combine these features into a single objective. If they try to do both at once from input designed to teach the full reward function, it is easy to end up with a representation that contains spurious correlations in the data, which fails to generalize to new settings. Instead, our ultimate goal is to enable robots to identify and isolate the causal features that people actually care about and use when they represent states and behavior. Our idea is that we can tune into this representation by asking users what behaviors they consider similar: behaviors will be similar if the features that matter are similar, even if low-level behavior is different; conversely, behaviors will be different if even one of the features that matter differs. This, in turn, is what enables the robot to disambiguate between what needs to go into the representation versus what is spurious, as well as what aspects of behavior can be compressed together versus not. The notion of learning representations based on similarity has a nice parallel in contrastive learning, a self-supervised representation learning technique that maps visually similar data points to similar embeddings, where similarity is defined by a designer through data augmentation heuristics. By contrast, in order to learn the representations that people use, so we can learn their preferences and objectives, we use their definition of similarity. In simulation as well as in a user study, we show that learning through such similarity queries leads to representations that, while far from perfect, are indeed more generalizable than self-supervised and task-input alternatives.

Inferring reward functions from human behavior is at the center of value alignment - aligning AI objectives with what we, humans, actually want. But doing so relies on models of how humans behave given their objectives. After decades of research in cognitive science, neuroscience, and behavioral economics, obtaining accurate human models remains an open research topic. This begs the question: how accurate do these models need to be in order for the reward inference to be accurate? On the one hand, if small errors in the model can lead to catastrophic error in inference, the entire framework of reward learning seems ill-fated, as we will never have perfect models of human behavior. On the other hand, if as our models improve, we can have a guarantee that reward accuracy also improves, this would show the benefit of more work on the modeling side. We study this question both theoretically and empirically. We do show that it is unfortunately possible to construct small adversarial biases in behavior that lead to arbitrarily large errors in the inferred reward. However, and arguably more importantly, we are also able to identify reasonable assumptions under which the reward inference error can be bounded linearly in the error in the human model. Finally, we verify our theoretical insights in discrete and continuous control tasks with simulated and human data.

Recent work in sim2real has successfully enabled robots to act in physical environments by training in simulation with a diverse ''population'' of environments (i.e. domain randomization). In this work, we focus on enabling generalization in assistive tasks: tasks in which the robot is acting to assist a user (e.g. helping someone with motor impairments with bathing or with scratching an itch). Such tasks are particularly interesting relative to prior sim2real successes because the environment now contains a human who is also acting. This complicates the problem because the diversity of human users (instead of merely physical environment parameters) is more difficult to capture in a population, thus increasing the likelihood of encountering out-of-distribution (OOD) human policies at test time. We advocate that generalization to such OOD policies benefits from (1) learning a good latent representation for human policies that test-time humans can accurately be mapped to, and (2) making that representation adaptable with test-time interaction data, instead of relying on it to perfectly capture the space of human policies based on the simulated population only. We study how to best learn such a representation by evaluating on purposefully constructed OOD test policies. We find that sim2real methods that encode environment (or population) parameters and work well in tasks that robots do in isolation, do not work well in assistance. In assistance, it seems crucial to train the representation based on the history of interaction directly, because that is what the robot will have access to at test time. Further, training these representations to then predict human actions not only gives them better structure, but also enables them to be fine-tuned at test-time, when the robot observes the partner act. https://adaptive-caregiver.github.io.

One of the most successful paradigms for reward learning uses human feedback in the form of comparisons. Although these methods hold promise, human comparison labeling is expensive and time consuming, constituting a major bottleneck to their broader applicability. Our insight is that we can greatly improve how effectively human time is used in these approaches by batching comparisons together, rather than having the human label each comparison individually. To do so, we leverage data dimensionality-reduction and visualization techniques to provide the human with a interactive GUI displaying the state space, in which the user can label subportions of the state space. Across some simple Mujoco tasks, we show that this high-level approach holds promise and is able to greatly increase the performance of the resulting agents, provided the same amount of human labeling time.

当从人类行为中推断出奖励功能（无论是演示，比较，物理校正或电子停靠点）时，它已证明对人类进行建模作为做出嘈杂的理性选择，并具有“合理性系数”，以捕获多少噪声或熵我们希望看到人类的行为。无论人类反馈的类型或质量如何，许多现有作品都选择修复此系数。但是，在某些情况下，进行演示可能要比回答比较查询要困难得多。在这种情况下，我们应该期望在示范中看到比比较中更多的噪音或次级临时性，并且应该相应地解释反馈。在这项工作中，我们提倡，将每种反馈类型的实际数据中的理性系数扎根，而不是假设默认值，对奖励学习具有重大的积极影响。我们在模拟反馈以及用户研究的实验中测试了这一点。我们发现，从单一反馈类型中学习时，高估人类理性可能会对奖励准确性和遗憾产生可怕的影响。此外，我们发现合理性层面会影响每种反馈类型的信息性：令人惊讶的是，示威并不总是最有用的信息 - 当人类的行为非常卑鄙时，即使在合理性水平相同的情况下，比较实际上就变得更加有用。 。此外，当机器人确定要要求的反馈类型时，它可以通过准确建模每种类型的理性水平来获得很大的优势。最终，我们的结果强调了关注假定理性级别的重要性，不仅是在从单个反馈类型中学习时，尤其是当代理商从多种反馈类型中学习时，尤其是在学习时。

本文研究了“探索性”机器学习分类问题的置信后的事后校准。这些问题的困难源于持续的愿望，即在策划数据集时具有足够的例子来推广哪些类别的界限以及对这些类别的有效性的混乱。我们认为，对于此类问题，必须使用“单一的所有”方法（顶级标签校准），而不是文献中其他地方提倡的“校准 - 满足 - 响应 - 摩托克质”方法。我们介绍并测试了四种旨在处理特定置信度估计的特质的新算法。这些方法中的主要主要是将内核密度比用于置信度校准，包括用于选择带宽的新颖的防弹算法。我们测试了我们的主张，并探讨了生物信息学应用程序（Phanns）1以及经典的MNIST基准2。最后，我们的分析认为，事后校准应始终执行，应仅基于测试数据集，并且应在视觉上进行理智检查。

冠状质量弹出（CME）是最地理化的空间天气现象，与大型地磁风暴有关，有可能引起电信，卫星网络中断，电网损失和故障的干扰。因此，考虑到这些风暴对人类活动的潜在影响，对CME的地理效果的准确预测至关重要。这项工作着重于在接近太阳CME的白光冠状动脉数据集中训练的不同机器学习方法，以估计这种新爆发的弹出是否有可能诱导地磁活动。我们使用逻辑回归，k-nearest邻居，支持向量机，向前的人工神经网络以及整体模型开发了二进制分类模型。目前，我们限制了我们的预测专门使用太阳能发作参数，以确保延长警告时间。我们讨论了这项任务的主要挑战，即我们数据集中的地理填充和无效事件的数量以及它们的众多相似之处以及可用变量数量有限的极端失衡。我们表明，即使在这种情况下，这些模型也可以达到足够的命中率。

我们如何才能训练辅助人机接口（例如，基于肌电图的肢体假体），将用户的原始命令信号转换为机器人或计算机的动作，如果没有事先映射，我们不能要求用户进行监督动作标签或奖励反馈的形式，我们对用户试图完成的任务没有事先了解？本文中的关键想法是，无论任务如何，当接口更直观时，用户的命令就会不那么嘈杂。我们将这一想法形式化为一个完全无监督的目标，以优化接口：用户的命令信号与环境中的诱导状态过渡之间的相互信息。为了评估此相互信息得分是否可以区分有效的界面和无效界面，我们对540K的示例进行了观察性研究，该示例的用户操作各种键盘和眼睛凝视接口，用于打字，控制模拟机器人和玩视频游戏。结果表明，我们的共同信息得分可预测各个领域中的基础任务完成指标，而Spearman的平均等级相关性为0.43。除了对现有接口的离线评估外，我们还使用无监督的目标从头开始学习接口：我们随机初始化接口，让用户尝试使用接口执行其所需的任务，测量相互信息得分并更新接口通过强化学习最大化相互信息。我们通过用户研究与12名参与者进行用户研究评估我们的方法，他们使用扰动的鼠标执行2D光标控制任务，并使用手势使用手势的一个用户玩《 Lunar Lander》游戏的实验。结果表明，我们可以在30分钟内从头开始学习一个接头，无需任何用户监督或任务的先验知识。