我们确定和研究政策流失的现象，即基于价值的强化学习中贪婪政策的快速变化。政策流失以惊人的快速步伐运作，改变了少数学习更新（在Atari上的DQN等典型的深层RL设置中）中大量州的贪婪行动。我们从经验上表征了现象，验证它不限于特定算法或环境特性。许多消融有助于削弱关于为什么流失仅与深度学习有关的少数相关的合理解释。最后，我们假设政策流失是一种有益但被忽视的隐性探索形式，它以新鲜的方式铸造了$ \ epsilon $ greedy探索，即$ \ epsilon $ - noise的作用比预期的要小得多。

深度学习（DL）模型为各种医学成像基准挑战提供了最先进的性能，包括脑肿瘤细分（BRATS）挑战。然而，局灶性病理多隔室分割（例如，肿瘤和病变子区）的任务特别具有挑战性，并且潜在的错误阻碍DL模型转化为临床工作流程。量化不确定形式的DL模型预测的可靠性，可以实现最不确定的地区的临床审查，从而建立信任并铺平临床翻译。最近，已经引入了许多不确定性估计方法，用于DL医学图像分割任务。开发指标评估和比较不确定性措施的表现将有助于最终用户制定更明智的决策。在本研究中，我们探索并评估在Brats 2019-2020任务期间开发的公制，以对不确定量化量化（Qu-Brats），并旨在评估和排列脑肿瘤多隔室分割的不确定性估计。该公制（1）奖励不确定性估计，对正确断言产生高置信度，以及在不正确的断言处分配低置信水平的估计数，（2）惩罚导致更高百分比的无关正确断言百分比的不确定性措施。我们进一步基准测试由14个独立参与的Qu-Brats 2020的分割不确定性，所有这些都参与了主要的Brats细分任务。总体而言，我们的研究结果证实了不确定性估计提供了分割算法的重要性和互补价值，因此突出了医学图像分析中不确定性量化的需求。我们的评估代码在HTTPS://github.com/ragmeh11/qu-brats公开提供。

异常气道扩张，称为牵引支气管扩张，是特发性肺纤维化（IPF）的典型特征。体积计算断层扫描（CT）成像捕获IPF中逐渐变细的丢失。我们假设气道异常的自动化量化可以提供IPF疾病程度和严重程度的估算。我们提出了一种自动化计算管道，系统地将气道树木从基于深度学习的气道分割中划分到其裂片和世代分支，从而从胸部CT获得气道结构措施。重要的是，透气阻止通过厚波传播的杂散气道分支的发生，并通过图表搜索去除气道树中的环，克服现有气道骨架算法的限制。在14名健康参与者和14名IPF患者之间比较了透气段（跨空间）和透气曲线曲线之间的逐渐变化。 IPF患者中，Airway interberering显着降低，与健康对照相比，Airway曲线曲调显着增加。差异在下叶中最大标记，符合IPF相关损伤的典型分布。透气是一种开源管道，避免了现有的气道定量算法的限制，并具有临床解释性。自动化气道测量可能具有作为IPF严重程度和疾病程度的新型成像生物标志物。

Deep reinforcement learning (RL) has achieved several high profile successes in difficult decision-making problems. However, these algorithms typically require a huge amount of data before they reach reasonable performance. In fact, their performance during learning can be extremely poor. This may be acceptable for a simulator, but it severely limits the applicability of deep RL to many real-world tasks, where the agent must learn in the real environment. In this paper we study a setting where the agent may access data from previous control of the system. We present an algorithm, Deep Q-learning from Demonstrations (DQfD), that leverages small sets of demonstration data to massively accelerate the learning process even from relatively small amounts of demonstration data and is able to automatically assess the necessary ratio of demonstration data while learning thanks to a prioritized replay mechanism. DQfD works by combining temporal difference updates with supervised classification of the demonstrator's actions. We show that DQfD has better initial performance than Prioritized Dueling Double Deep Q-Networks (PDD DQN) as it starts with better scores on the first million steps on 41 of 42 games and on average it takes PDD DQN 83 million steps to catch up to DQfD's performance. DQfD learns to out-perform the best demonstration given in 14 of 42 games. In addition, DQfD leverages human demonstrations to achieve state-of-the-art results for 11 games. Finally, we show that DQfD performs better than three related algorithms for incorporating demonstration data into DQN.

The ability to learn tasks in a sequential fashion is crucial to the development of artificial intelligence. Neural networks are not, in general, capable of this and it has been widely thought that catastrophic forgetting is an inevitable feature of connectionist models. We show that it is possible to overcome this limitation and train networks that can maintain expertise on tasks which they have not experienced for a long time. Our approach remembers old tasks by selectively slowing down learning on the weights important for those tasks. We demonstrate our approach is scalable and effective by solving a set of classification tasks based on the MNIST hand written digit dataset and by learning several Atari 2600 games sequentially.

Experience replay lets online reinforcement learning agents remember and reuse experiences from the past. In prior work, experience transitions were uniformly sampled from a replay memory. However, this approach simply replays transitions at the same frequency that they were originally experienced, regardless of their significance. In this paper we develop a framework for prioritizing experience, so as to replay important transitions more frequently, and therefore learn more efficiently. We use prioritized experience replay in Deep Q-Networks (DQN), a reinforcement learning algorithm that achieved human-level performance across many Atari games. DQN with prioritized experience replay achieves a new stateof-the-art, outperforming DQN with uniform replay on 41 out of 49 games.

We demonstrate a proof-of-concept of a large language model conducting corporate lobbying related activities. We use an autoregressive large language model (OpenAI's text-davinci-003) to determine if proposed U.S. Congressional bills are relevant to specific public companies and provide explanations and confidence levels. For the bills the model deems as relevant, the model drafts a letter to the sponsor of the bill in an attempt to persuade the congressperson to make changes to the proposed legislation. We use hundreds of ground-truth labels of the relevance of a bill to a company to benchmark the performance of the model, which outperforms the baseline of predicting the most common outcome of irrelevance. However, we test the ability to determine the relevance of a bill with the previous OpenAI GPT-3 model (text-davinci-002), which was state-of-the-art on many language tasks until text-davinci-003 was released on November 28, 2022. The performance of text-davinci-002 is worse than simply always predicting that a bill is irrelevant to a company. These results suggest that, as large language models continue to improve core natural language understanding capabilities, performance on corporate lobbying related tasks will continue to improve. We then discuss why this could be problematic for societal-AI alignment.

Hybrid unmanned aerial vehicles (UAVs) integrate the efficient forward flight of fixed-wing and vertical takeoff and landing (VTOL) capabilities of multicopter UAVs. This paper presents the modeling, control and simulation of a new type of hybrid micro-small UAVs, coined as lifting-wing quadcopters. The airframe orientation of the lifting wing needs to tilt a specific angle often within $ 45$ degrees, neither nearly $ 90$ nor approximately $ 0$ degrees. Compared with some convertiplane and tail-sitter UAVs, the lifting-wing quadcopter has a highly reliable structure, robust wind resistance, low cruise speed and reliable transition flight, making it potential to work fully-autonomous outdoor or some confined airspace indoor. In the modeling part, forces and moments generated by both lifting wing and rotors are considered. Based on the established model, a unified controller for the full flight phase is designed. The controller has the capability of uniformly treating the hovering and forward flight, and enables a continuous transition between two modes, depending on the velocity command. What is more, by taking rotor thrust and aerodynamic force under consideration simultaneously, a control allocation based on optimization is utilized to realize cooperative control for energy saving. Finally, comprehensive Hardware-In-the-Loop (HIL) simulations are performed to verify the advantages of the designed aircraft and the proposed controller.

Variational autoencoders model high-dimensional data by positing low-dimensional latent variables that are mapped through a flexible distribution parametrized by a neural network. Unfortunately, variational autoencoders often suffer from posterior collapse: the posterior of the latent variables is equal to its prior, rendering the variational autoencoder useless as a means to produce meaningful representations. Existing approaches to posterior collapse often attribute it to the use of neural networks or optimization issues due to variational approximation. In this paper, we consider posterior collapse as a problem of latent variable non-identifiability. We prove that the posterior collapses if and only if the latent variables are non-identifiable in the generative model. This fact implies that posterior collapse is not a phenomenon specific to the use of flexible distributions or approximate inference. Rather, it can occur in classical probabilistic models even with exact inference, which we also demonstrate. Based on these results, we propose a class of latent-identifiable variational autoencoders, deep generative models which enforce identifiability without sacrificing flexibility. This model class resolves the problem of latent variable non-identifiability by leveraging bijective Brenier maps and parameterizing them with input convex neural networks, without special variational inference objectives or optimization tricks. Across synthetic and real datasets, latent-identifiable variational autoencoders outperform existing methods in mitigating posterior collapse and providing meaningful representations of the data.

We introduce Argoverse 2 (AV2) - a collection of three datasets for perception and forecasting research in the self-driving domain. The annotated Sensor Dataset contains 1,000 sequences of multimodal data, encompassing high-resolution imagery from seven ring cameras, and two stereo cameras in addition to lidar point clouds, and 6-DOF map-aligned pose. Sequences contain 3D cuboid annotations for 26 object categories, all of which are sufficiently-sampled to support training and evaluation of 3D perception models. The Lidar Dataset contains 20,000 sequences of unlabeled lidar point clouds and map-aligned pose. This dataset is the largest ever collection of lidar sensor data and supports self-supervised learning and the emerging task of point cloud forecasting. Finally, the Motion Forecasting Dataset contains 250,000 scenarios mined for interesting and challenging interactions between the autonomous vehicle and other actors in each local scene. Models are tasked with the prediction of future motion for "scored actors" in each scenario and are provided with track histories that capture object location, heading, velocity, and category. In all three datasets, each scenario contains its own HD Map with 3D lane and crosswalk geometry - sourced from data captured in six distinct cities. We believe these datasets will support new and existing machine learning research problems in ways that existing datasets do not. All datasets are released under the CC BY-NC-SA 4.0 license.