自成立以来，建立在广泛任务中表现出色的普通代理的任务一直是强化学习的重要目标。这个问题一直是对Alarge工作体系的研究的主题，并且经常通过观察Atari 57基准中包含的广泛范围环境的分数来衡量的性能。 Agent57是所有57场比赛中第一个超过人类基准的代理商，但这是以数据效率差的代价，需要实现近800亿帧的经验。以Agent57为起点，我们采用了各种各样的形式，以降低超过人类基线所需的经验200倍。在减少数据制度和Propose有效的解决方案时，我们遇到了一系列不稳定性和瓶颈，以构建更强大，更有效的代理。我们还使用诸如Muesli和Muzero之类的高性能方法证明了竞争性的性能。 TOOUR方法的四个关键组成部分是（1）近似信任区域方法，该方法可以从TheOnline网络中稳定引导，（2）损失和优先级的归一化方案，在学习具有广泛量表的一组值函数时，可以提高鲁棒性， （3）改进的体系结构采用了NFNET的技术技术来利用更深的网络而无需标准化层，并且（4）政策蒸馏方法可使瞬时贪婪的策略加班。

The deep reinforcement learning community has made several independent improvements to the DQN algorithm. However, it is unclear which of these extensions are complementary and can be fruitfully combined. This paper examines six extensions to the DQN algorithm and empirically studies their combination. Our experiments show that the combination provides state-of-the-art performance on the Atari 2600 benchmark, both in terms of data efficiency and final performance. We also provide results from a detailed ablation study that shows the contribution of each component to overall performance.

In recent years there have been many successes of using deep representations in reinforcement learning. Still, many of these applications use conventional architectures, such as convolutional networks, LSTMs, or auto-encoders. In this paper, we present a new neural network architecture for model-free reinforcement learning. Our dueling network represents two separate estimators: one for the state value function and one for the state-dependent action advantage function. The main benefit of this factoring is to generalize learning across actions without imposing any change to the underlying reinforcement learning algorithm. Our results show that this architecture leads to better policy evaluation in the presence of many similar-valued actions. Moreover, the dueling architecture enables our RL agent to outperform the state-of-the-art on the Atari 2600 domain.

Modeling lies at the core of both the financial and the insurance industry for a wide variety of tasks. The rise and development of machine learning and deep learning models have created many opportunities to improve our modeling toolbox. Breakthroughs in these fields often come with the requirement of large amounts of data. Such large datasets are often not publicly available in finance and insurance, mainly due to privacy and ethics concerns. This lack of data is currently one of the main hurdles in developing better models. One possible option to alleviating this issue is generative modeling. Generative models are capable of simulating fake but realistic-looking data, also referred to as synthetic data, that can be shared more freely. Generative Adversarial Networks (GANs) is such a model that increases our capacity to fit very high-dimensional distributions of data. While research on GANs is an active topic in fields like computer vision, they have found limited adoption within the human sciences, like economics and insurance. Reason for this is that in these fields, most questions are inherently about identification of causal effects, while to this day neural networks, which are at the center of the GAN framework, focus mostly on high-dimensional correlations. In this paper we study the causal preservation capabilities of GANs and whether the produced synthetic data can reliably be used to answer causal questions. This is done by performing causal analyses on the synthetic data, produced by a GAN, with increasingly more lenient assumptions. We consider the cross-sectional case, the time series case and the case with a complete structural model. It is shown that in the simple cross-sectional scenario where correlation equals causation the GAN preserves causality, but that challenges arise for more advanced analyses.

We present the interpretable meta neural ordinary differential equation (iMODE) method to rapidly learn generalizable (i.e., not parameter-specific) dynamics from trajectories of multiple dynamical systems that vary in their physical parameters. The iMODE method learns meta-knowledge, the functional variations of the force field of dynamical system instances without knowing the physical parameters, by adopting a bi-level optimization framework: an outer level capturing the common force field form among studied dynamical system instances and an inner level adapting to individual system instances. A priori physical knowledge can be conveniently embedded in the neural network architecture as inductive bias, such as conservative force field and Euclidean symmetry. With the learned meta-knowledge, iMODE can model an unseen system within seconds, and inversely reveal knowledge on the physical parameters of a system, or as a Neural Gauge to "measure" the physical parameters of an unseen system with observed trajectories. We test the validity of the iMODE method on bistable, double pendulum, Van der Pol, Slinky, and reaction-diffusion systems.

We propose Hierarchical ProtoPNet: an interpretable network that explains its reasoning process by considering the hierarchical relationship between classes. Different from previous methods that explain their reasoning process by dissecting the input image and finding the prototypical parts responsible for the classification, we propose to explain the reasoning process for video action classification by dissecting the input video frames on multiple levels of the class hierarchy. The explanations leverage the hierarchy to deal with uncertainty, akin to human reasoning: When we observe water and human activity, but no definitive action it can be recognized as the water sports parent class. Only after observing a person swimming can we definitively refine it to the swimming action. Experiments on ActivityNet and UCF-101 show performance improvements while providing multi-level explanations.

Artificial intelligence (AI) in the form of deep learning bears promise for drug discovery and chemical biology, $\textit{e.g.}$, to predict protein structure and molecular bioactivity, plan organic synthesis, and design molecules $\textit{de novo}$. While most of the deep learning efforts in drug discovery have focused on ligand-based approaches, structure-based drug discovery has the potential to tackle unsolved challenges, such as affinity prediction for unexplored protein targets, binding-mechanism elucidation, and the rationalization of related chemical kinetic properties. Advances in deep learning methodologies and the availability of accurate predictions for protein tertiary structure advocate for a $\textit{renaissance}$ in structure-based approaches for drug discovery guided by AI. This review summarizes the most prominent algorithmic concepts in structure-based deep learning for drug discovery, and forecasts opportunities, applications, and challenges ahead.

The ability to convert reciprocating, i.e., alternating, actuation into rotary motion using linkages is hindered fundamentally by their poor torque transmission capability around kinematic singularity configurations. Here, we harness the elastic potential energy of a linear spring attached to the coupler link of four-bar mechanisms to manipulate force transmission around the kinematic singularities. We developed a theoretical model to explore the parameter space for proper force transmission in slider-crank and rocker-crank four-bar kinematics. Finally, we verified the proposed model and methodology by building and testing a macro-scale prototype of a slider-crank mechanism. We expect this approach to enable the development of small-scale rotary engines and robotic devices with closed kinematic chains dealing with serial kinematic singularities, such as linkages and parallel manipulators.

Prevailing methods for assessing and comparing generative AIs incentivize responses that serve a hypothetical representative individual. Evaluating models in these terms presumes homogeneous preferences across the population and engenders selection of agglomerative AIs, which fail to represent the diverse range of interests across individuals. We propose an alternative evaluation method that instead prioritizes inclusive AIs, which provably retain the requisite knowledge not only for subsequent response customization to particular segments of the population but also for utility-maximizing decisions.

We study the problem of combining neural networks with symbolic reasoning. Recently introduced frameworks for Probabilistic Neurosymbolic Learning (PNL), such as DeepProbLog, perform exponential-time exact inference, limiting the scalability of PNL solutions. We introduce Approximate Neurosymbolic Inference (A-NeSI): a new framework for PNL that uses neural networks for scalable approximate inference. A-NeSI 1) performs approximate inference in polynomial time without changing the semantics of probabilistic logics; 2) is trained using data generated by the background knowledge; 3) can generate symbolic explanations of predictions; and 4) can guarantee the satisfaction of logical constraints at test time, which is vital in safety-critical applications. Our experiments show that A-NeSI is the first end-to-end method to scale the Multi-digit MNISTAdd benchmark to sums of 15 MNIST digits, up from 4 in competing systems. Finally, our experiments show that A-NeSI achieves explainability and safety without a penalty in performance.