Inspired by recent progress in multi-agent Reinforcement Learning (RL), in this work we examine the collective intelligent behaviour of theoretical universal agents by introducing a weighted mixture operation. Given a weighted set of agents, their weighted mixture is a new agent whose expected total reward in any environment is the corresponding weighted average of the original agents' expected total rewards in that environment. Thus, if RL agent intelligence is quantified in terms of performance across environments, the weighted mixture's intelligence is the weighted average of the original agents' intelligences. This operation enables various interesting new theorems that shed light on the geometry of RL agent intelligence, namely: results about symmetries, convex agent-sets, and local extrema. We also show that any RL agent intelligence measure based on average performance across environments, subject to certain weak technical conditions, is identical (up to a constant factor) to performance within a single environment dependent on said intelligence measure.
Universal Empathy and Ethical Bias for Artificial General Intelligence
AIDEUS;National Research University of Information Technology, Mechanics and Optics(国立信息技术、机械与光学大学);Aix Marseille Université(艾克斯-马赛大学);CNRS(法国国家科学研究中心)
Embedded Universal Predictive Intelligence: a coherent framework for multi-agent learning
Google(谷歌);Mila - Quebec AI Institute(Mila-魁北克人工智能研究所);Université de Montréal(蒙特利尔大学);McGill University(麦吉尔大学);CIFAR(加拿大高等研究院);ETH Zürich(苏黎世联邦理工学院);Google DeepMind(谷歌DeepMind);Santa Fe Institute(圣塔菲研究所)
Universal Algorithmic Intelligence: A mathematical top->down approach
序贯决策理论正式解决了不确定世界中的理性主体问题,如果真实的环境先验概率分布是已知的。Solomonoff的泛归纳理论形式化地解决了未知先验分布的序列预测问题。我们将这两种思想结合起来,得到一个无参数的通用人工智能理论。我们给出了强有力的论据,由此产生的AIXI模型是最智能的无偏代理可能。我们概述了AIXI模型如何正式解决一些问题类,包括序列预测,战略游戏,功能最小化,强化和监督学习。AIXI模型的主要缺点是它是不可计算的。为了克服这个问题,我们构造了一个修改后的算法AIXITl,它仍然有效地比任何其他时间t和长度l有界代理更智能。AIXITl的计算时间是t x 2^l的数量级。讨论了智能顺序关系的形式化定义、视界问题以及AIXI理论与其他人工智能方法的关系。
Has Multimodal Learning Delivered Universal Intelligence in Healthcare? A Comprehensive Survey
Saw Swee Hock School of Public Health, National University of Singapore(新加坡国立大学公共健康学院);School of Computer Science, Beijing University of Posts and Telecommunications(北京邮电大学计算机学院);School of Automation, Northwestern Polytechnical University(西北工业大学自动化学院);School of Computer Science and Technology, Xi’an Jiaotong University(西安交通大学计算机科学与技术学院)
Mixture of Universal Experts: Scaling Virtual Width via Depth-Width Transformation
Institute of Information Engineering, Chinese Academy of Sciences(中国科学院信息工程研究所);School of Cyber Security, University of Chinese Academy of Sciences(中国科学院大学网络安全学院);Baidu Inc(百度公司)
Towards a Universal Theory of Artificial Intelligence based on Algorithmic Probability and Sequential Decision Theory
决策理论正式解决了不确定世界中理性主体的问题,如果真实的环境概率分布是已知的。Solomonoff的泛归纳理论形式化地解决了未知分布的序列预测问题。我们统一了这两种理论,并给出了强有力的论据,由此产生的通用AIXI模型在任何可计算的环境中表现最佳。AIXI模型的主要缺点是它是不可计算的。为了克服这个问题,我们构造了一个改进的算法AIXI^tl,它仍然优于任何其他时间t和空间l有界代理。AIXI^tl的计算时间为t x 2^l的数量级。
Revisiting Citizen Science Through the Lens of Hybrid Intelligence
Center for Hybrid Intelligence(混合智能中心);University of Gothenburg(哥德堡大学);Centre for Collective Intelligence Design(集体智能设计中心);Citizen Cyberlab(公民网络实验室);Ben Gurion University(本古里安大学);University of Oxford(牛津大学);Northwestern University(西北大学);Vencortex(Vencortex公司);University College London(伦敦大学学院);Human Computation Institute(人类计算研究所)
First Draft on the xInf Model for Universal Physical Computation and Reverse Engineering of Natural Intelligence
Suzhou Institute of Biomedical Engineering and Technology, Chinese Academy of Sciences(中国科学院苏州生物医学工程技术研究所);Technical University Munich(慕尼黑工业大学);Third Military Medical University(第三军医大学);Beijing AboroTech Co., Ltd.(北京AboroTech有限公司);Chongqing U-LaborTech Co., Ltd.(重庆U-LaborTech有限公司)