Deep Reinforcement Learning (RL) agents are susceptible to adversarial noise in their observations that can mislead their policies and decrease their performance. However, an adversary may be interested not only in decreasing the reward, but also in modifying specific temporal logic properties of the policy. This paper presents a metric that measures the exact impact of adversarial attacks against such properties. We use this metric to craft optimal adversarial attacks. Furthermore, we introduce a model checking method that allows us to verify the robustness of RL policies against adversarial attacks. Our empirical analysis confirms (1) the quality of our metric to craft adversarial attacks against temporal logic properties, and (2) that we are able to concisely assess a system's robustness against attacks.

本文介绍了Cool-MC，这是一种集成了最先进的加固学习（RL）和模型检查的工具。具体而言，该工具建立在OpenAI健身房和概率模型检查器风暴上。COOL-MC提供以下功能：（1）模拟器在OpenAI体育馆训练RL政策，用于Markov决策过程（MDPS），这些模拟器定义为暴风雨的输入，（2）使用“ SORM”的新型号构建器，用于使用回调功能要验证（神经网络）RL策略，（3）与OpenAI Gym或Storm中指定的模型和政策相关的正式抽象，以及（4）算法以获得有关所谓允许政策的性能的界限。我们描述了Cool-MC的组件和体系结构，并在多个基准环境中演示了其功能。

Compliance in actuation has been exploited to generate highly dynamic maneuvers such as throwing that take advantage of the potential energy stored in joint springs. However, the energy storage and release could not be well-timed yet. On the contrary, for multi-link systems, the natural system dynamics might even work against the actual goal. With the introduction of variable stiffness actuators, this problem has been partially addressed. With a suitable optimal control strategy, the approximate decoupling of the motor from the link can be achieved to maximize the energy transfer into the distal link prior to launch. However, such continuous stiffness variation is complex and typically leads to oscillatory swing-up motions instead of clear launch sequences. To circumvent this issue, we investigate decoupling for speed maximization with a dedicated novel actuator concept denoted Bi-Stiffness Actuation. With this, it is possible to fully decouple the link from the joint mechanism by a switch-and-hold clutch and simultaneously keep the elastic energy stored. We show that with this novel paradigm, it is not only possible to reach the same optimal performance as with power-equivalent variable stiffness actuation, but even directly control the energy transfer timing. This is a major step forward compared to previous optimal control approaches, which rely on optimizing the full time-series control input.

Participants in political discourse employ rhetorical strategies -- such as hedging, attributions, or denials -- to display varying degrees of belief commitments to claims proposed by themselves or others. Traditionally, political scientists have studied these epistemic phenomena through labor-intensive manual content analysis. We propose to help automate such work through epistemic stance prediction, drawn from research in computational semantics, to distinguish at the clausal level what is asserted, denied, or only ambivalently suggested by the author or other mentioned entities (belief holders). We first develop a simple RoBERTa-based model for multi-source stance predictions that outperforms more complex state-of-the-art modeling. Then we demonstrate its novel application to political science by conducting a large-scale analysis of the Mass Market Manifestos corpus of U.S. political opinion books, where we characterize trends in cited belief holders -- respected allies and opposed bogeymen -- across U.S. political ideologies.

Knowledge distillation (KD) has gained a lot of attention in the field of model compression for edge devices thanks to its effectiveness in compressing large powerful networks into smaller lower-capacity models. Online distillation, in which both the teacher and the student are learning collaboratively, has also gained much interest due to its ability to improve on the performance of the networks involved. The Kullback-Leibler (KL) divergence ensures the proper knowledge transfer between the teacher and student. However, most online KD techniques present some bottlenecks under the network capacity gap. By cooperatively and simultaneously training, the models the KL distance becomes incapable of properly minimizing the teacher's and student's distributions. Alongside accuracy, critical edge device applications are in need of well-calibrated compact networks. Confidence calibration provides a sensible way of getting trustworthy predictions. We propose BD-KD: Balancing of Divergences for online Knowledge Distillation. We show that adaptively balancing between the reverse and forward divergences shifts the focus of the training strategy to the compact student network without limiting the teacher network's learning process. We demonstrate that, by performing this balancing design at the level of the student distillation loss, we improve upon both performance accuracy and calibration of the compact student network. We conducted extensive experiments using a variety of network architectures and show improvements on multiple datasets including CIFAR-10, CIFAR-100, Tiny-ImageNet, and ImageNet. We illustrate the effectiveness of our approach through comprehensive comparisons and ablations with current state-of-the-art online and offline KD techniques.

The xView2 competition and xBD dataset spurred significant advancements in overhead building damage detection, but the competition's pixel level scoring can lead to reduced solution performance in areas with tight clusters of buildings or uninformative context. We seek to advance automatic building damage assessment for disaster relief by proposing an auxiliary challenge to the original xView2 competition. This new challenge involves a new dataset and metrics indicating solution performance when damage is more local and limited than in xBD. Our challenge measures a network's ability to identify individual buildings and their damage level without excessive reliance on the buildings' surroundings. Methods that succeed on this challenge will provide more fine-grained, precise damage information than original xView2 solutions. The best-performing xView2 networks' performances dropped noticeably in our new limited/local damage detection task. The common causes of failure observed are that (1) building objects and their classifications are not separated well, and (2) when they are, the classification is strongly biased by surrounding buildings and other damage context. Thus, we release our augmented version of the dataset with additional object-level scoring metrics https://gitlab.kitware.com/dennis.melamed/xfbd to test independence and separability of building objects, alongside the pixel-level performance metrics of the original competition. We also experiment with new baseline models which improve independence and separability of building damage predictions. Our results indicate that building damage detection is not a fully-solved problem, and we invite others to use and build on our dataset augmentations and metrics.

Filming sport videos from an aerial view has always been a hard and an expensive task to achieve, especially in sports that require a wide open area for its normal development or the ones that put in danger human safety. Recently, a new solution arose for aerial filming based on the use of Unmanned Aerial Vehicles (UAVs), which is substantially cheaper than traditional aerial filming solutions that require conventional aircrafts like helicopters or complex structures for wide mobility. In this paper, we describe the design process followed for building a customized UAV suitable for sports aerial filming. The process includes the requirements definition, technical sizing and selection of mechanical, hardware and software technologies, as well as the whole integration and operation settings. One of the goals is to develop technologies allowing to build low cost UAVs and to manage them for a wide range of usage scenarios while achieving high levels of flexibility and automation. This work also shows some technical issues found during the development of the UAV as well as the solutions implemented.

Our goal with this survey is to provide an overview of the state of the art deep learning technologies for face generation and editing. We will cover popular latest architectures and discuss key ideas that make them work, such as inversion, latent representation, loss functions, training procedures, editing methods, and cross domain style transfer. We particularly focus on GAN-based architectures that have culminated in the StyleGAN approaches, which allow generation of high-quality face images and offer rich interfaces for controllable semantics editing and preserving photo quality. We aim to provide an entry point into the field for readers that have basic knowledge about the field of deep learning and are looking for an accessible introduction and overview.

Database research can help machine learning performance in many ways. One way is to design better data structures. This paper combines the use of incremental computation and sequential and probabilistic filtering to enable "forgetful" tree-based learning algorithms to cope with concept drift data (i.e., data whose function from input to classification changes over time). The forgetful algorithms described in this paper achieve high time performance while maintaining high quality predictions on streaming data. Specifically, the algorithms are up to 24 times faster than state-of-the-art incremental algorithms with at most a 2% loss of accuracy, or at least twice faster without any loss of accuracy. This makes such structures suitable for high volume streaming applications.

Reinforcement Learning (RL) can enable agents to learn complex tasks. However, it is difficult to interpret the knowledge and reuse it across tasks. Inductive biases can address such issues by explicitly providing generic yet useful decomposition that is otherwise difficult or expensive to learn implicitly. For example, object-centered approaches decompose a high dimensional observation into individual objects. Expanding on this, we utilize an inductive bias for explicit object-centered knowledge separation that provides further decomposition into semantic representations and dynamics knowledge. For this, we introduce a semantic module that predicts an objects' semantic state based on its context. The resulting affordance-like object state can then be used to enrich perceptual object representations. With a minimal setup and an environment that enables puzzle-like tasks, we demonstrate the feasibility and benefits of this approach. Specifically, we compare three different methods of integrating semantic representations into a model-based RL architecture. Our experiments show that the degree of explicitness in knowledge separation correlates with faster learning, better accuracy, better generalization, and better interpretability.