This paper is a technical overview of DeepMind and Google's recent work on reinforcement learning for controlling commercial cooling systems. Building on expertise that began with cooling Google's data centers more efficiently, we recently conducted live experiments on two real-world facilities in partnership with Trane Technologies, a building management system provider. These live experiments had a variety of challenges in areas such as evaluation, learning from offline data, and constraint satisfaction. Our paper describes these challenges in the hope that awareness of them will benefit future applied RL work. We also describe the way we adapted our RL system to deal with these challenges, resulting in energy savings of approximately 9% and 13% respectively at the two live experiment sites.

本文讨论了具有丰富记录数据的域中的政策选择问题，但互动预算有限。解决此问题将在行业，机器人和推荐领域中安全评估和部署离线强化学习政策等。已经提出了几种违规评估（OPE）技术以评估仅使用记录数据的策略的值。然而，OPE的评估与真实环境中的完整在线评估之间仍然存在巨大差距。然而，在实践中通常不可能进行大量的在线互动。为了克服这个问题，我们介绍了\ emph {主动脱机策略选择} - 一种新的顺序决策方法，将记录数据与在线交互相结合，以识别最佳策略。这种方法使用ope估计来热启动在线评估。然后，为了利用有限的环境相互作用，我们决定基于具有表示政策相似性的内核函数的贝叶斯优化方法来评估哪个策略。我们使用大量候选政策的多个基准，以表明所提出的方法提高了最先进的OPE估计和纯在线策略评估。

我们研究如何构建一组可以组成的政策来解决一个加强学习任务的集合。每个任务都是不同的奖励函数，被定义为已知功能的线性组合。我们考虑一下我们呼吁改进政策的特定策略组合（SIPS）：给定一套政策和一系列任务，SIP是前者的任何构成，其性能至少与其成分的表现相当好所有任务。我们专注于啜饮的最保守的实例化，Set-Max政策（SMPS），因此我们的分析扩展到任何SIP。这包括已知的策略组合运营商，如广义政策改进。我们的主要贡献是一种策略迭代算法，构建一组策略，以最大限度地提高所得SMP的最坏情况性能。该算法通过连续向集合添加新策略来工作。我们表明，生成的SMP的最坏情况性能严格地改善了每次迭代，并且算法仅在不存在导致改进性能的策略时停止。我们经验在网格世界上进行了验证评估了算法，也是来自DeepMind控制套件的一组域。我们确认了我们关于我们算法的单调性能的理论结果。有趣的是，我们还经验展示了算法计算的政策集是多样的，导致网格世界中的不同轨迹以及控制套件中的非常独特的运动技能。

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.

Previous work has shown the potential of deep learning to predict renal obstruction using kidney ultrasound images. However, these image-based classifiers have been trained with the goal of single-visit inference in mind. We compare methods from video action recognition (i.e. convolutional pooling, LSTM, TSM) to adapt single-visit convolutional models to handle multiple visit inference. We demonstrate that incorporating images from a patient's past hospital visits provides only a small benefit for the prediction of obstructive hydronephrosis. Therefore, inclusion of prior ultrasounds is beneficial, but prediction based on the latest ultrasound is sufficient for patient risk stratification.

Its numerous applications make multi-human 3D pose estimation a remarkably impactful area of research. Nevertheless, assuming a multiple-view system composed of several regular RGB cameras, 3D multi-pose estimation presents several challenges. First of all, each person must be uniquely identified in the different views to separate the 2D information provided by the cameras. Secondly, the 3D pose estimation process from the multi-view 2D information of each person must be robust against noise and potential occlusions in the scenario. In this work, we address these two challenges with the help of deep learning. Specifically, we present a model based on Graph Neural Networks capable of predicting the cross-view correspondence of the people in the scenario along with a Multilayer Perceptron that takes the 2D points to yield the 3D poses of each person. These two models are trained in a self-supervised manner, thus avoiding the need for large datasets with 3D annotations.

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.

Plastic shopping bags that get carried away from the side of roads and tangled on cotton plants can end up at cotton gins if not removed before the harvest. Such bags may not only cause problem in the ginning process but might also get embodied in cotton fibers reducing its quality and marketable value. Therefore, it is required to detect, locate, and remove the bags before cotton is harvested. Manually detecting and locating these bags in cotton fields is labor intensive, time-consuming and a costly process. To solve these challenges, we present application of four variants of YOLOv5 (YOLOv5s, YOLOv5m, YOLOv5l and YOLOv5x) for detecting plastic shopping bags using Unmanned Aircraft Systems (UAS)-acquired RGB (Red, Green, and Blue) images. We also show fixed effect model tests of color of plastic bags as well as YOLOv5-variant on average precision (AP), mean average precision (mAP@50) and accuracy. In addition, we also demonstrate the effect of height of plastic bags on the detection accuracy. It was found that color of bags had significant effect (p < 0.001) on accuracy across all the four variants while it did not show any significant effect on the AP with YOLOv5m (p = 0.10) and YOLOv5x (p = 0.35) at 95% confidence level. Similarly, YOLOv5-variant did not show any significant effect on the AP (p = 0.11) and accuracy (p = 0.73) of white bags, but it had significant effects on the AP (p = 0.03) and accuracy (p = 0.02) of brown bags including on the mAP@50 (p = 0.01) and inference speed (p < 0.0001). Additionally, height of plastic bags had significant effect (p < 0.0001) on overall detection accuracy. The findings reported in this paper can be useful in speeding up removal of plastic bags from cotton fields before harvest and thereby reducing the amount of contaminants that end up at cotton gins.

Applications such as employees sharing office spaces over a workweek can be modeled as problems where agents are matched to resources over multiple rounds. Agents' requirements limit the set of compatible resources and the rounds in which they want to be matched. Viewing such an application as a multi-round matching problem on a bipartite compatibility graph between agents and resources, we show that a solution (i.e., a set of matchings, with one matching per round) can be found efficiently if one exists. To cope with situations where a solution does not exist, we consider two extensions. In the first extension, a benefit function is defined for each agent and the objective is to find a multi-round matching to maximize the total benefit. For a general class of benefit functions satisfying certain properties (including diminishing returns), we show that this multi-round matching problem is efficiently solvable. This class includes utilitarian and Rawlsian welfare functions. For another benefit function, we show that the maximization problem is NP-hard. In the second extension, the objective is to generate advice to each agent (i.e., a subset of requirements to be relaxed) subject to a budget constraint so that the agent can be matched. We show that this budget-constrained advice generation problem is NP-hard. For this problem, we develop an integer linear programming formulation as well as a heuristic based on local search. We experimentally evaluate our algorithms on synthetic networks and apply them to two real-world situations: shared office spaces and matching courses to classrooms.

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.