Domain adaptation is a common problem in robotics, with applications such as transferring policies from simulation to real world and lifelong learning. Performing such adaptation, however, requires informative data about the environment to be available during the adaptation. In this paper, we present domain curiosity -- a method of training exploratory policies that are explicitly optimized to provide data that allows a model to learn about the unknown aspects of the environment. In contrast to most curiosity methods, our approach explicitly rewards learning, which makes it robust to environment noise without sacrificing its ability to learn. We evaluate the proposed method by comparing how much a model can learn about environment dynamics given data collected by the proposed approach, compared to standard curious and random policies. The evaluation is performed using a toy environment, two simulated robot setups, and on a real-world haptic exploration task. The results show that the proposed method allows data-efficient and accurate estimation of dynamics.
CUDC: A Curiosity-Driven Unsupervised Data Collection Method with Adaptive Temporal Distances for Offline Reinforcement Learning
Alibaba-NTU Singapore Joint Research Institute（阿里巴巴-南洋理工大学新加坡联合研究院）；Nanyang Technological University（南洋理工大学）；Joint NTU-UBC Research Centre of Excellence in Active Living for the Elderly（南洋理工大学-不列颠哥伦比亚大学活跃养老卓越研究中心）；Centre for Frontier AI Research（前沿人工智能研究中心）；Agency for Science, Technology and Research（新加坡科技研究局）
How Useful is Causal Invariance for Domain Adaptation in Finite-Sample Settings?
Department of Computer Science, ETH Zurich（苏黎世联邦理工学院计算机科学系）；Causal Artificial Intelligence Lab, Columbia University（哥伦比亚大学因果人工智能实验室）；Department of Statistics, Columbia University（哥伦比亚大学统计系）
First, Learn What You Don't Know: Active Information Gathering for Driving at the Limits of Handling
Toyota Research Institute（丰田研究院）；Department of Mechanical Engineering, Rice University（机械工程系， Rice大学）；MANE, Rensselaer Polytechnic Institute（MANE，Rensselaer理工学院）
针对极限动态驾驶中在线学习滞后易致失控的问题，提出结合贝叶斯最后一层元学习与不确定性引导主动数据收集的车辆动力学辨识框架，并在 Toyota Supra 漂移实验中验证其可靠控制效果。
DIDA: Denoised Imitation Learning based on Domain Adaptation
National Key Laboratory for Novel Software Technology, Nanjing University（南京大学计算机软件新技术国家重点实验室）；School of Artificial Intelligence, Nanjing University（南京大学人工智能学院）；School of ZZZ（ZZZ学院）
$φ$-Adapt: A Physics-Informed Adaptation Learning Approach to 2D Quantum Material Discovery
Department of Electrical Engineering and Computer Science, University of Arkansas（电气工程与计算机科学系，阿肯色大学）；Department of Physics, Montana State University（物理系，蒙塔纳州立大学）；Department of Physics, University of Arkansas（物理系，阿肯色大学）
Causal Direction of Data Collection Matters: Implications of Causal and Anticausal Learning for NLP
Max Planck Institute for Intelligent Systems（马克斯·普朗克智能系统研究所）；ETH Zürich（苏黎世联邦理工学院）；University of Cambridge（剑桥大学）；University College London（伦敦大学学院）；IIT Kharagpur（印度理工学院卡拉格普尔分校）
Towards Unified Multi-task EEG Analysis with Low-Rank Adaptation
Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所）；School of Artifcial Intelligence, University of Chinese Academy of Sciences（中国科学院大学人工智能学院）；State Key Laboratory of Brain Cognition（脑认知国家重点实验室）；Beijing Academy of Artificial Intelligence（北京人工智能研究院）；State Key Laboratory of Multimedia Information Processing, Peking University（北京大学多媒体信息处理国家重点实验室）
Cross-Domain Structure Preserving Projection for Heterogeneous Domain Adaptation
Department of Computer Science, Durham University（达勒姆大学计算机科学系）
异构领域自适应（HDA）解决了迁移学习问题，其中来自源和目标领域的数据具有不同的模态（例如，文本和图像）或特征尺寸（例如，用不同方法提取的特征）。这对于多模态数据分析是有用的。传统的领域自适应算法假设源样本和目标样本的表示位于同一特征空间，因此很可能无法解决异构领域自适应问题。当代国家的最先进的HDA方法通常是由复杂的优化目标的有利的性能，因此是计算昂贵的和较难推广。为了解决这些问题，我们提出了一种新的跨域结构保持投影（CDSPP）算法的HDA。作为经典LPP到异构域的扩展，CDSPP旨在学习特定于域的投影，将源域和目标域的样本特征映射到公共子空间，从而保持类一致性并充分对齐数据分布。CDSPP是简单的，并通过求解广义特征值问题具有确定性的解决方案。它自然适用于监督HDA，但也已扩展为半监督HDA，其中未标记的目标域样本可用。在HDA的常用基准数据集（即NIC-Caltech，Multilingual Reuters Collection，NUS-WIDE-ImageNet）上进行了广泛的实验，以及我们首次为HDA引入的NIC-Home数据集，因为它的类数量明显多于现有的数据集（65 vs 10，6和8）。监督和半监督HDA的实验结果表明，我们提出的方法对当代国家的最先进的方法的优越性能。
Domain Borders Are There to Be Crossed With Federated Few-Shot Adaptation
Faculty of Computer Science and Business Information Systems（计算机科学与商业信息系统系）；Technical University of Applied Sciences Würzburg-Schweinfurt（应用技术大学Würzburg-Schweinfurt）；Faculty of Technology（技术系）；Bielefeld University（比勒菲尔德大学）；Center for Artificial Intelligence（人工智能中心）；IAV GmbH
