2022 IEEE CoG将于8月21日-8月24日线上召开,多名国内外顶级科学家将在本次大会上带来前沿报告!本届大会由极悦娱乐承办,这也是该会议第一次在中国举行。大会报告将进行线上直播,具体报告信息如下,敬请关注!
Keynote I
On Game-Based Control Systems
报告人:郭雷
中科院国家数学与交叉科学中心主任
极悦注册院士
报告时间:8月21日9:00-10:00
报告简介:
In the traditional control systems theory, the plant to be controlled or regulated usually does not have its own payoff function, and much progress in both theory and applications has been made in this fields. However, in many practical systems such as those in social, economic and the future “intelligent” engineering systems, the dynamical systems to be regulated may have their own objectives to pursue, which may not be the same as that of the global regulator or controller. Such hierarchical decision making dynamical systems may be called as game-based control systems (GBCS), where the system models may contain various uncertainties and the global regulator can be feedback signals. This lecture will present some backgrounds and examples for introducing GBCS , followed by an investigation of some basic characteristics and properties of GBCS. It will be shown how the macro-states of the GBCS may be regulated by intervening the Nash equilibrium that is reached at the micro-level. In particular, we will present some basic results on global controllability and stabilizability of linear GBCS with multi-players at the micro-level. Both deterministic and stochastic systems will be investigated, and a main technical issue involves the analysis and control of forward-backward (stochastic) differential equations.
报告人介绍:
郭雷,1982年毕业于山东大学数学系, 1987年在中科院系统科学所获博士学位。现任中科院数学与系统科学研究院研究员、中科院国家数学与交叉科学中心主任。曾任中科院数学与系统科学研究院院长、中国工业与应用数学会理事长等。
主要从事系统与控制科学研究,特别是自适应估计、自适应滤波、自适应控制、自适应博弈、PID控制理论、随机与非线性不确定性系统控制、反馈机制最大能力与局限、群体系统集体行为、博弈控制系统和复杂系统科学等方面的研究。
1998年当选美国 IEEE 会士,2001年当选极悦注册院士。随后当选发展中国家科学院院士,瑞典皇家工程科学院外籍院士,国际自动控制联合会会士,并被瑞典皇家理工学院(KTH)授予荣誉博士学位。曾获国际自动控制联合会(IFAC)颁发的青年作者奖和杰出服务奖等。2019年他“因对自适应控制、系统辨识、自适应信号处理、随机系统及应用数学领域的根本性和实际性贡献”而获IEEE控制系统学会颁发的波德奖(Hendrik W. Bode Lecture Prize)。
曾先后两次应邀在三年一度的IFAC世界大会上作大会报告(1999,2014),在四年一度的国际数学家大会(ICM)上作邀请报告(2002),并在IEEE决策与控制会议(CDC)上作大会报告(2019)。
个人网页:
http://lsc.amss.cas.cn/guolei/grjj/
Keynote 2
Emotion-Centric AI: from Hubris and Nemesis to Catharsis
报告人:Georgios N. Yannakakis
马耳他大学数字游戏研究所所长/教授
modl.ai联合创始人
报告时间:8月21日15:00-16:00
报告简介:
Why bother about emotions and their computation? Why is emotion such a critical element of every aspect of AI and Games research nowadays? How can emotion help us test games, represent the games we play, design creative AI algorithms, offer reliable agency to AI, and ultimately understand player experience?
In this talk, I will attempt to address these questions through a series of milestone research studies (hubris) that led to a number of key lessons learned over the years (nemesis). I will conclude the talk by suggesting directions through which emotion can reframe the ways we build AI algorithms and develop games (catharsis).
报告人介绍:
Georgios N Yannakakis, 2006年获得爱丁堡大学信息学博士学位,现任美国马耳他大学(UM)数字游戏研究所所长、教授,也是modl.ai的联合创始人。
主要研究兴趣在于人工智能、计算创造力、情感计算、高级游戏技术和人机交互的交叉领域,所从事的研究内容包括用户体验建模与面向娱乐、教育、培训和健康的个性化交互系统程序化内容生成。
研究得到欧洲和许多国家的资助(包括玛丽Sk?odowska-Curie奖学金),已发表学术论文260余篇,得到《科学》杂志和《新科学家》等报道。现任IEEE Transactions on Games主编,IEEE Transactions on Evolutionary Computation的副编辑,曾任IEEE Transactions on Affective Computing的副编辑。曾任游戏人工智能领域(IEEE CIG 2010)和游戏研究领域(FDG 2013, FDG 2020)大会的总主席。是《人工智能与游戏》教材的合著者,也是《人工智能与游戏》暑期学校系列课程的协办者。
个人网页:
https://yannakakis.net
Keynote 3
Going beyond Games:Towards Decision Making in The Real-world
报告人:田渊栋
Meta人工智能研究院研究员/研究经理
报告时间:8月22日9:00-10:00
报告简介:
Deep Reinforcement Learning (DRL), as a smart search technique that dynamically improves its policy and value estimation based on observation given previous data, has shown human-level or even super-human performance for games such as Go, chess and Starcraft. On the other hand, when applying DRL in real-world applications, new challenges emerge such as effective integration with current working systems, learning representation of large state and action spaces, or even redefining the temporal structure of sequential decision making.
In this talk, I will cover our recent works that include learning initial solutions to the existing solver, learning state representations, or even learning the structure of sequential decision itself.
报告人介绍:
田渊栋,Meta人工智能研究院研究员和研究经理,研究兴趣包括深度强化学习、表示学习和优化,是2021年ICML杰出论文荣誉奖和2013年ICCV Marr荣誉奖的获得者。他是ELF OpenGo项目的首席科学家和工程师。在此之前,于2013-2014年在谷歌自动驾驶汽车团队工作,并于2013年获得卡耐基梅隆大学机器人研究所博士学位。
个人网页:
https://yuandong-tian.com/
Keynote 4
Agent-Human Complex Games for Multi-agent Studies
报告人:Sarit Kraus
以色列巴伊兰大学计算机科学教授
以色列科学与人文学院院士
报告时间:8月22日16:00-17:00
报告简介:
Intelligent computer agents are increasingly being deployed in group settings in which they interact with people in order to carry out tasks. To operate effectively in such settings, computer agents need capabilities for making decisions and negotiating with other participants—both people and computer-based agents. To construct effective agent strategies, it is almost impossible to use only a purely analytical approach, but there is a need to learn and evaluate agent strategies empirically in specific domains. In the talk, we will discuss five types of domains: (i) real applications such as agents for road safety; (ii) simulations of real applications such as autonomous car simulations; (iii) complex, off-the-shelf games such as Diplomacy or card games; (iv) designed games for the specific research questions such as the Colored Trails environment; and (v) abstract simple games such as the Ultimatum game. For each of the domain types, we will present several examples and demonstrate their use in agents’ development and evaluation. We will discuss the advantages and the challenges of agent studies in each of the settings.
报告人介绍:
Sarit Kraus,1989年获得以色列希伯来大学计算机科学博士,现任以色列巴伊兰大学计算机科学教授。
主要研究兴趣是人工智能,特别是多主体系统,重点关注如何设计智能主体,使之能够与人熟练地互动。研究合作和对抗的博弈场景,攻关建模人类的行为、预测人类的决策,以及开发主体决策的模型等挑战。Kraus教授具体研究机器学习、决策理论和博弈论、非经典逻辑、不确定性下的优化和心理学等方法和算法,以及在物理安防、智能汽车、人类培训、推荐系统、自动谈判和调解、虚拟人和康复等方面的应用。
鉴于智能主体和多主体系统(包括人和机器人)方面的贡献,获得IJCAI计算机与思想奖、美国计算机学会SIGART自主主体研究奖、美国计算机学会雅典娜讲座奖、美国计算机学会EMET奖,并两次获得美国计算机学会IFAAMAS有影响力论文奖。Kraus教授是AAAI, ECCAI和ACM会士,也是高级ERC资助的获得者,是以色列科学与人文学院院士。
个人网页:
https://u.cs.biu.ac.il/~krauss/
Keynote 5
An Unquenchable Appetite:Games, Play, and Climate Change
报告人:Jessica Hammer
卡内基梅隆大学人机交互研究所副教授
报告时间:8月23日9:00-10:00
报告简介:
Mitigating climate change is an urgent challenge. It is also an extremely difficult one, not just from a climate systems perspective but from the perspective of mobilizing effective action. Barriers include understanding complex systems, supporting collective action, and resisting climate despair. While these are hard problems, they are also ones where games can help. In this talk, we will explore how game designers can contribute our knowledge and expertise to this grand challenge.
报告人介绍:
Jessica Hammer,1999年获得美国哈佛大学计算机科学学士学位,2002年获得美国纽约大学交互通信硕士学位,2014年获得美国哥伦比亚大学教育认知研究博士学位,现任美国卡内基梅隆大学(CMU)人机交互研究所(HCII)副教授。
主要研究兴趣为游戏心理学,专注于设计影响玩家的想法和感受的特定游戏;设计使人们的生活变得更好的游戏;研究游戏如何改变人们的思考、感觉和行为方式等。
个人网页:
https://hcii.cmu.edu/people/jessica-hammer
Keynote 6
Player-AI Interaction: What Can HumanCentered AI Learn from Computer Games and Other Creative Domains
报告人:Jichen Zhu
哥本哈根信息技术大学数字设计专业副教授
Procedural eXpression Lab负责人
报告时间:8月23日16:00-17:00
报告简介:
Recent growth in artificial intelligence and machine learning propels human-AI interaction, especially with endusers, to the forefront of HCI research. Among the fast-growing body of literature on human-AI interaction design, an overlooked area is the context of play and playful interaction. Since computer games naturally focus on end-user experience, the fields of game AI and game design have accumulated decades of valuable design knowledge. In this talk, we will synthesize the current trends of player-AI interaction and discuss how they can advance broader open problems in Human-Center AI, such as interpretability/explainability, trust and ethics, and human-machine collaboration. Built on examples from recent AI-based games and digital art, we will propose open problems in the design and technical implementation of player-AI interaction.
报告人介绍:
Jichen Zhu, 2002年获得加拿大麦吉尔(McGill)大学学士学位,2004年获得卡内基梅隆大学(CMU)娱乐技术硕士学位,2009年获得佐治亚理工大学(GIT)计算机科学硕士学位、数字媒体博士学位,现任丹麦哥本哈根信息技术大学(IT University of Copenhagen)数字设计专业的副教授,是Procedural eXpression Lab (PXL)负责人。
主要研究方向是人机交互、交互/游戏设计和人工智能,重点关注设计和开发新型的人机交互,特别是个性化的学习和健康游戏。
合著了80多篇同行评议的研究论文,并获得了包括2021年数字游戏基础大会(FDG)最佳论文奖在内的多篇最佳论文奖。她的研究得到了美国国家科学基金会、国家卫生研究所和诺和北欧基金会的资助。担任麻省理工大学出版社软件研究丛书的联合编辑,也是数字游戏科学进步协会(SASDG)的董事会成员。
个人网页:
https://pure.itu.dk/portal/en/persons/jichen-zhu(e383647f-00d3-41b1-ad95-ff69bdfffb42).html
Keynote 7
On Computation Characterization in Game Theory
报告人:邓小铁
重庆大学前沿计算研究中心教授
欧洲科学院外籍院士
报告时间:8月24日14:00-15:00
报告简介:
We discuss the line of research approach in understanding the computational wisdom of game theory, in terms of rationality, complexity, and dynamics.
报告人介绍:
邓小铁,1982年于清华大学获得学士学位,1984年于极悦注册获得硕士学位,1989年于斯坦福大学获得博士学位。2017年12月入职重庆大学,任信息科学技术学院前沿计算研究中心讲席教授。
主要研究兴趣包括算法博弈论、均衡和机制设计、互联网广告系统、云计算定价及资源分配、社交网络行为分析及推荐系统,以及交通及物流网络算法。
2008年因在博弈论算法的贡献获选ACM会士,2019年因在部分信息和交互环境中计算的贡献获选IEEE会士,2020年获选欧洲科学院外籍院士,2021年当选中国工业与应用数学学会会士。作为项目负责人,曾承担十几项加拿大、香港、英国,及国家基金委科研项目,并担任多种国际期刊编委,多个国际学术会议主席。发表论文200余篇,被引用数千次;多次做国际学术会议特邀报告;曾获得IEEE理论计算机学术会议FOCS的最佳论文奖,2015年度高等学校科学研究优秀成果奖 (自然科学)二等奖(排名第二)。应用方面获得多项美国专利及国家专利,曾担任主要互联网公司机制设计顾问。
个人网页:
https://cfcs.pku.edu.cn/people/faculty/xiaotiedeng/index.htm
Keynote 8
AlphaStar: Grandmaster Level in StarCraft II using Multi-agent Reinforcement Learning
报告人:Oriol Vinyals
DeepMind首席科学家
深度学习小组负责人
报告时间:8月24日20:00-21:00
报告简介:
Games have been used for decades as an important way to test and evaluate the performance of artificial intelligence systems. As capabilities have increased, the research community has sought games with increasing complexity that capture different elements of intelligence required to solve scientific and real-world problems. In recent years, StarCraft, considered to be one of the most challenging Real-Time Strategy (RTS) games and one of the longest-played esports of all time, has emerged by consensus as a “grand challenge” for AI research.
In this talk, I will introduce our StarCraft II program AlphaStar, the first Artificial Intelligence to reach Grandmaster status without any game restrictions. The focus will be on the technical contributions which made possible this milestone in AI, and which yielded a cover in the prestigious journal Nature. To end, I'll also reflect on what has happened since the release of AlphaStar.
报告人介绍:
Oriol Vinyals,谷歌DeepMind的首席科学家、深度学习小组的负责人,工作重点是深度学习和人工智能。在加入DeepMind之前,Oriol是谷歌Brain团队的一员。他获得加州大学伯克利分校的EECS博士学位,是2016年麻省理工学院TR35创新者奖的获得者。研究被《纽约时报》、《金融时报》、《连线》、BBC等多次报道,文章被引用超过7万次。学术任职包括2017年和2018年学习表征国际会议(ICLR)的程序委员会主席,也曾多次担任NeurIPS和ICML会议的区域主席。一些贡献如seq2seq,知识蒸馏,TensorFlow等被谷歌翻译,语音合成,语音识别使用,提供每天数十亿次的查询。作为AlphaStar项目的首席研究员,创新地提出了AlphaStar,击败了《星际争霸》游戏的人类特级大师,论文登上了《自然》杂志的封面。在DeepMind,Oriol持续致力于研究感兴趣的人工智能领域,尤其是机器学习、深度学习和强化学习。
个人网页:
https://research.google/people/OriolVinyals/
观看方式:大会将在“极悦娱乐”哔哩哔哩直播间、视频号进行直播,8月21日-24日准时开始,敬请期待!
哔哩哔哩直播间
微信视频号