我们在面对未衡量的混杂因素时研究离线增强学习（RL）。由于缺乏与环境的在线互动，离线RL面临以下两个重大挑战：（i）代理可能会被未观察到的状态变量混淆； （ii）提前收集的离线数据不能为环境提供足够的覆盖范围。为了应对上述挑战，我们借助工具变量研究了混杂的MDP中的政策学习。具体而言，我们首先建立了基于和边缘化的重要性采样（MIS）的识别结果，以确定混杂的MDP中的预期总奖励结果。然后，通过利用悲观主义和我们的认同结果，我们提出了各种政策学习方法，并具有有限样本的次级临时性保证，可以在最小的数据覆盖范围和建模假设下找到最佳的课堂政策。最后，我们广泛的理论研究和一项由肾脏移植动机的数值研究证明了该方法的有希望的表现。

1972年出现了经典的COX模型，促进了如何使用生物医学中的事实分析来量化患者预后的突破。该模型最有用的特征之一是分析中变量的解释性。但是，这是以引入有关回归模型功能形式的强有力的假设的代价。为了打破这一差距，本文旨在利用新的套索神经网络在间隔进行审查的设置中利用经典COX模型的解释性优势，该网络同时选择最相关的变量，同时量化预测因子和生存时间之间的非线性关系。在广泛的模拟研究中，新方法的增益在经验上进行了说明，其中涉及线性和非线性地面依赖性的示例。我们还证明了我们在NHANES 2003-2006波的生理，临床和加速度计分析中的策略表现，以预测体育活动对患者存活的影响。我们的方法的表现优于使用传统Cox模型的文献中的先前结果。

基于森林的方法最近在非参数治疗效应估计中获得了普及。在这一工作方面，我们引入了因果生存森林，可用于在可能右估计结果的生存和观察环境中估计异质治疗效果。我们的方法依赖于正交估计方程来在不满意的情况下对审查和选择效果进行鲁棒性调整。在我们的实验中，我们发现相对于许多基线的表现良好的方法。

While the capabilities of autonomous systems have been steadily improving in recent years, these systems still struggle to rapidly explore previously unknown environments without the aid of GPS-assisted navigation. The DARPA Subterranean (SubT) Challenge aimed to fast track the development of autonomous exploration systems by evaluating their performance in real-world underground search-and-rescue scenarios. Subterranean environments present a plethora of challenges for robotic systems, such as limited communications, complex topology, visually-degraded sensing, and harsh terrain. The presented solution enables long-term autonomy with minimal human supervision by combining a powerful and independent single-agent autonomy stack, with higher level mission management operating over a flexible mesh network. The autonomy suite deployed on quadruped and wheeled robots was fully independent, freeing the human supervision to loosely supervise the mission and make high-impact strategic decisions. We also discuss lessons learned from fielding our system at the SubT Final Event, relating to vehicle versatility, system adaptability, and re-configurable communications.

Recent advances in upper limb prostheses have led to significant improvements in the number of movements provided by the robotic limb. However, the method for controlling multiple degrees of freedom via user-generated signals remains challenging. To address this issue, various machine learning controllers have been developed to better predict movement intent. As these controllers become more intelligent and take on more autonomy in the system, the traditional approach of representing the human-machine interface as a human controlling a tool becomes limiting. One possible approach to improve the understanding of these interfaces is to model them as collaborative, multi-agent systems through the lens of joint action. The field of joint action has been commonly applied to two human partners who are trying to work jointly together to achieve a task, such as singing or moving a table together, by effecting coordinated change in their shared environment. In this work, we compare different prosthesis controllers (proportional electromyography with sequential switching, pattern recognition, and adaptive switching) in terms of how they present the hallmarks of joint action. The results of the comparison lead to a new perspective for understanding how existing myoelectric systems relate to each other, along with recommendations for how to improve these systems by increasing the collaborative communication between each partner.

Nonnegative matrix factorization can be used to automatically detect topics within a corpus in an unsupervised fashion. The technique amounts to an approximation of a nonnegative matrix as the product of two nonnegative matrices of lower rank. In this paper, we show this factorization can be combined with regression on a continuous response variable. In practice, the method performs better than regression done after topics are identified and retrains interpretability.

As language models (LMs) scale, they develop many novel behaviors, good and bad, exacerbating the need to evaluate how they behave. Prior work creates evaluations with crowdwork (which is time-consuming and expensive) or existing data sources (which are not always available). Here, we automatically generate evaluations with LMs. We explore approaches with varying amounts of human effort, from instructing LMs to write yes/no questions to making complex Winogender schemas with multiple stages of LM-based generation and filtering. Crowdworkers rate the examples as highly relevant and agree with 90-100% of labels, sometimes more so than corresponding human-written datasets. We generate 154 datasets and discover new cases of inverse scaling where LMs get worse with size. Larger LMs repeat back a dialog user's preferred answer ("sycophancy") and express greater desire to pursue concerning goals like resource acquisition and goal preservation. We also find some of the first examples of inverse scaling in RL from Human Feedback (RLHF), where more RLHF makes LMs worse. For example, RLHF makes LMs express stronger political views (on gun rights and immigration) and a greater desire to avoid shut down. Overall, LM-written evaluations are high-quality and let us quickly discover many novel LM behaviors.

The number of international benchmarking competitions is steadily increasing in various fields of machine learning (ML) research and practice. So far, however, little is known about the common practice as well as bottlenecks faced by the community in tackling the research questions posed. To shed light on the status quo of algorithm development in the specific field of biomedical imaging analysis, we designed an international survey that was issued to all participants of challenges conducted in conjunction with the IEEE ISBI 2021 and MICCAI 2021 conferences (80 competitions in total). The survey covered participants' expertise and working environments, their chosen strategies, as well as algorithm characteristics. A median of 72% challenge participants took part in the survey. According to our results, knowledge exchange was the primary incentive (70%) for participation, while the reception of prize money played only a minor role (16%). While a median of 80 working hours was spent on method development, a large portion of participants stated that they did not have enough time for method development (32%). 25% perceived the infrastructure to be a bottleneck. Overall, 94% of all solutions were deep learning-based. Of these, 84% were based on standard architectures. 43% of the respondents reported that the data samples (e.g., images) were too large to be processed at once. This was most commonly addressed by patch-based training (69%), downsampling (37%), and solving 3D analysis tasks as a series of 2D tasks. K-fold cross-validation on the training set was performed by only 37% of the participants and only 50% of the participants performed ensembling based on multiple identical models (61%) or heterogeneous models (39%). 48% of the respondents applied postprocessing steps.

As AI systems become more capable, we would like to enlist their help to supervise other AIs. We experiment with methods for training a harmless AI assistant through self-improvement, without any human labels identifying harmful outputs. The only human oversight is provided through a list of rules or principles, and so we refer to the method as 'Constitutional AI'. The process involves both a supervised learning and a reinforcement learning phase. In the supervised phase we sample from an initial model, then generate self-critiques and revisions, and then finetune the original model on revised responses. In the RL phase, we sample from the finetuned model, use a model to evaluate which of the two samples is better, and then train a preference model from this dataset of AI preferences. We then train with RL using the preference model as the reward signal, i.e. we use 'RL from AI Feedback' (RLAIF). As a result we are able to train a harmless but non-evasive AI assistant that engages with harmful queries by explaining its objections to them. Both the SL and RL methods can leverage chain-of-thought style reasoning to improve the human-judged performance and transparency of AI decision making. These methods make it possible to control AI behavior more precisely and with far fewer human labels.

Variational autoencoders (VAEs) are powerful tools for learning latent representations of data used in a wide range of applications. In practice, VAEs usually require multiple training rounds to choose the amount of information the latent variable should retain. This trade-off between the reconstruction error (distortion) and the KL divergence (rate) is typically parameterized by a hyperparameter $\beta$. In this paper, we introduce Multi-Rate VAE (MR-VAE), a computationally efficient framework for learning optimal parameters corresponding to various $\beta$ in a single training run. The key idea is to explicitly formulate a response function that maps $\beta$ to the optimal parameters using hypernetworks. MR-VAEs construct a compact response hypernetwork where the pre-activations are conditionally gated based on $\beta$. We justify the proposed architecture by analyzing linear VAEs and showing that it can represent response functions exactly for linear VAEs. With the learned hypernetwork, MR-VAEs can construct the rate-distortion curve without additional training and can be deployed with significantly less hyperparameter tuning. Empirically, our approach is competitive and often exceeds the performance of multiple $\beta$-VAEs training with minimal computation and memory overheads.