Determining what experience to generate to best facilitate learning (i.e. exploration) is one of the distinguishing features and open challenges in reinforcement learning. The advent of distributed agents that interact with parallel instances of the environment has enabled larger scales and greater flexibility, but has not removed the need to tune exploration to the task, because the ideal data for the learning algorithm necessarily depends on its process of learning. We propose to dynamically adapt the data generation by using a non-stationary multi-armed bandit to optimize a proxy of the learning progress. The data distribution is controlled by modulating multiple parameters of the policy (such as stochasticity, consistency or optimism) without significant overhead. The adaptation speed of the bandit can be increased by exploiting the factored modulation structure. We demonstrate on a suite of Atari 2600 games how this unified approach produces results comparable to per-task tuning at a fraction of the cost.
Residual Learning from Demonstration: Adapting DMPs for Contact-rich Manipulation
University of Edinburgh（爱丁堡大学）；Aalto University（阿尔托大学）；Monash University（莫纳什大学）；Intrinsic（Intrinsic公司）；Facebook AI Research（脸书人工智能研究院）
涉及接触和摩擦的操作技能是许多机器人任务所固有的。使用类的电机原语钉孔一样插入，我们研究机器人如何学习这些技能。动态运动原语（Dynamic Movement Primitives，缩写为DMOR）是一种通过行为克隆（Behavior Cloning，缩写为BC）提取此类策略的流行方法，但在插入上下文中可能会遇到困难。策略自适应策略，如剩余学习，可以帮助提高策略的整体性能，在接触丰富的操纵。然而，目前尚不清楚如何最好地使用DMP。因此，我们考虑了几种可能的方法来适应一个学习的公式，并提出了“残余示教学习”（rLfD），一个框架，结合DMPS与强化学习（RL）学习残余校正策略。我们的评估表明，直接在任务空间中应用残差学习并在机器人的完整姿势上操作可以显着提高DMPs的整体性能。我们发现，rLfD提供了一个温和的关节解决方案，提高了任务的成功和推广的DMPS \rb{and enables transfer to different geometries and frictions through few-shot task adaptation}。根据一系列任务对拟议框架进行评价。一个模拟机器人和一个物理机器人必须成功地将钉子、齿轮和插头插入各自的插座。本文附带的其他材料和视频可在https://sites.google.com/view/rlfd/上找到。
Improving healthcare access management by predicting patient no-show behaviour
Southampton Business School, University of Southampton（南安普顿大学南安普顿商学院）；Pontificia Universidad Javeriana（哈维里亚那天主教大学）；The University of Western Ontario（西安大略大学）；Mathematical Sciences, University of Southampton（南安普顿大学数学科学学院）
Deep learning and abstractive summarisation for radiological reports: an empirical study for adapting the PEGASUS models' family with scarce data
Institute of AI and Informatics in Medicine (AIIM) TUM University Hospital, Technical University of Munich, Munich, Germany（人工智能与医学信息学研究所（AIIM）慕尼黑技术大学医院，慕尼黑技术大学，慕尼黑，德国）；Chair of Medical Informatics, Institute of Artificial Intelligence and Informatics in Medicine (AIIM), TUM University Hospital, Technical University of Munich, Munich, Germany（医学信息学教授，人工智能与医学信息学研究所（AIIM），慕尼黑技术大学医院，慕尼黑技术大学，慕尼黑，德国）；Department of Biomedical Informatics, Research Group MIDorAI, Medical Faculty Mannheim, Heidelberg University, Mannheim, Germany（生物医学信息学系，MIDorAI研究组，海德堡大学曼海姆医学院，曼海姆，德国）
Don't Fool Me Twice: Adapting to Adversity in the Wild with Experience-Driven Reasoning
Department of Engineering Design, Indian Institute of Technology, Madras（印度理工学院工程设计系，马德拉斯）；Robotics Institute, Carnegie Mellon University（卡内基梅隆大学机器人研究所）
REVE: A Foundation Model for EEG -- Adapting to Any Setup with Large-Scale Pretraining on 25,000 Subjects
IMT Atlantique Lab-STICC UMR CNRS 6285（IMT Atlantique 实验室）；Psychology Department Université de Montréal（蒙特利尔大学心理学系）；Mila (Quebec AI research institute)（魁北克人工智能研究院）；UNIQUE (Quebec Neuro-AI research center)（魁北克神经人工智能研究中心）
