Reinforcement learning (RL) is a general paradigm for studying intelligent behaviour, with applications ranging from artificial intelligence to psychology and economics. AIXI is a universal solution to the RL problem; it can learn any computable environment. A technical subtlety of AIXI is that it is defined using a mixture over semimeasures that need not sum to 1, rather than over proper probability measures. In this work we argue that the shortfall of a semimeasure can naturally be interpreted as the agent's estimate of the probability of its death. We formally define death for generally intelligent agents like AIXI, and prove a number of related theorems about their behaviour. Notable discoveries include that agent behaviour can change radically under positive linear transformations of the reward signal (from suicidal to dogmatically self-preserving), and that the agent's posterior belief that it will survive increases over time.
Uncovering Misattributed Suicide Causes through Annotation Inconsistency Detection in Death Investigation Notes
Cockrell School of Engineering, The University of Texas at Austin（德克萨斯大学奥斯汀分校科克雷尔工程学院）；Weill Cornell Medicine（威尔康奈尔医学院）；School of Political Science and Public Administration, Shandong University（山东大学政治学与公共管理学院）；Mayo Clinic（梅奥诊所）；School of Information, The University of Texas at Austin（德克萨斯大学奥斯汀分校信息学院）
Analysis and Evaluation of Explainable Artificial Intelligence on Suicide Risk Assessment
The University of Western Australia（西澳大利亚大学）；Armadale Mental Health Service（阿玛代尔心理健康服务中心）；Bethesda Clinic（贝塞斯达诊所）；Co-HIVE Mental Health（Co-HIVE心理健康中心）；Harry Perkins Institute of Medical Research（哈里·珀金斯医学研究所）；Fiona Stanley Hospital（菲奥娜·斯坦利医院）；University of Western Australia（西澳大利亚大学）
Reinforcement Learning for Intelligent Healthcare Systems: A Comprehensive Survey
College of Science and Engineering, Hamad Bin Khalifa University, Qatar Foundation（卡塔尔基金会哈马德·本·哈利法大学科学与工程学院）；College of Engineering, Qatar University（卡塔尔大学工程学院）
Breaking Bad News in the Era of Artificial Intelligence and Algorithmic Medicine: An Exploration of Disclosure and its Ethical Justification using the Hedonic Calculus
Imperial College London（帝国理工学院）；University of Bayreuth（拜罗伊特大学）
Secure and Privacy-Preserving Automated Machine Learning Operations into End-to-End Integrated IoT-Edge-Artificial Intelligence-Blockchain Monitoring System for Diabetes Mellitus Prediction
The University of Melbourne（墨尔本大学）；United Arab Emirates University（阿联酋大学）；Mediclinic（Mediclinic医疗集团）；Bhubaneswar Institute of Technology（布巴内斯瓦尔理工学院）；SRM Institute of Science & Technology（SRM科学技术学院）
Artificial Intelligence-Based Opportunistic Coronary Calcium Screening in the Veterans Affairs National Healthcare System
Veterans Affairs Long Beach Healthcare System（退伍军人事务部长滩医疗系统）；University of California, Irvine（加州大学欧文分校）；Veterans Health Administration（退伍军人健康管理局）；University of Colorado School of Public Health（科罗拉多大学公共卫生学院）；Veterans Affairs Kansas City Healthcare System（退伍军人事务部堪萨斯城医疗系统）；Veterans Affairs San Diego Healthcare System（退伍军人事务部圣迭戈医疗系统）；University of California, San Diego（加州大学圣迭戈分校）；Mass General Brigham（麻省总医院布莱根医疗系统）；Harvard Medical School（哈佛医学院）；Brigham and Women's Hospital（布莱根妇女医院）；Dana-Farber Cancer Institute（丹娜-法伯癌症研究所）；Maastricht University（马斯特里赫特大学）
