深度强化学习：现实中回合制策略游戏
演讲摘要：Numerous attempts have been made to apply artificial intelligence (AI) technologies to the real world outside confined laboratory environments. This is a hard problem since the real world has numerous variables that vary over time, which can have a profound effect on the performance of AI. Moreover, the real world has high uncertainties, which are too complex and too ill-defined to be modeled with the necessary accuracy. Thus it becomes necessary to encompass uncertainty into the modeling and furthermore to measure and approximate changes in real world environments.
This work has chosen to use the complex strategy game of curling as a test bed for demonstrating the interaction of an AI system and the real (slippery) world. Note that the curling ice sheet is an environment with highly varying uncertainty that has a profound effect on the throw performance; humans require years of practice to master the game that has complex strategic elements, as well as the throw itself.
We demonstrate an AI curling robot system named `Curly' that competes on a real world curling ice sheet. Curly encompasses (1) an AI-based curling strategy and simulation engine under consideration of the high `icy' uncertainty, (2) the thrower robot enabled by autonomous driving with traction control, and (3) the skip robot that allows recognizing the curling field and stone configuration based on vision technology. The Curly performed well both: in classical game situations and when interacting with human opponents, namely, the top-ranked Korean woman curling team.
人们曾多次尝试将人工智能（AI）技术应用在实验室环境之外的真实世界里。这是一个很难解决的问题，因为现实世界中有许多随时间变化的变量，这些变量会对人工智能的性能产生重要的影响。此外，现实世界具有很高的不确定性，且过于复杂和定义不清，根本不具备必要的精度进行建模。因此，有必要将不确定性纳入建模，并进一步测量和估算现实环境中的变化。
本文选择了复杂的冰壶策略游戏作为实验平台，演示了人工智能系统与真实（滑）世界的交互作用。需要注意的是，冰壶冰盖是一个复杂多变、不确定性的环境，对投掷性能有很大影响；人们需要经过多年的练习来掌握这种复杂策略元素的游戏，还有投掷动作。
我们演示了名为"Curly 科利"的人工智能冰壶机器人系统，在真实的冰壶赛场上进行比赛。科利系统包括（1）考虑了冰面的不确定性，建立的基于人工智能的冰壶策略和模拟引擎；（2）自动驱动加牵引控制的抛掷机器人；（3）能识别基于视觉技术的冰壶场地和石材结构的跳跃机器人。科利系统无论是在传统的游戏环境，还是与人类对手（即排名第一的韩国女子冰壶队）互动时都表现得很好。
讲者简介：Seong-Whan Lee is a full professor at Korea University, where he is the head of the Department of Artificial Intelligence.
He received the B.S. degree in computer science and statistics from Seoul National University, Seoul, Korea, in 1984, and the M.S. and Ph.D. degrees in computer science from Korea Advanced Institute of Science and Technology in 1986 and 1989, respectively.
From February 1989 to February 1995, he was an Assistant Professor in the Department of Computer Science at Chungbuk National University, Cheongju, Korea. In March 1995, he joined the faculty of the Department of Computer Science and Engineering at Korea University, Seoul, Korea, and now he is the tenured full professor. In 2001, he stayed at the Department of Brain and Cognitive Sciences, MIT as a visiting professor.
A Fellow of the IAPR(1998), IEEE(2009), and Korean Academy of Science and Technology(2009), he has served several professional societies as chairman or governing board member. He was the founding Editor-in-Chief of the International Journal of Document Analysis and Recognition and has been an Associate Editor of several international journals: Pattern Recognition, ACM Trans. on Applied Perception, IEEE Trans. on Affective Computing, Image and Vision Computing, International Journal of Pattern Recognition and Artificial Intelligence, and International Journal of Image and Graphics. He is the founding president of the Korean Society for Artificial Intelligence.
His research interests include pattern recognition, artificial intelligence, and brain engineering. He has more than 500 publications in international journals and conference proceedings, and authored 10 books.
Seong-Whan Lee 是高丽大学的全职教授，人工智能系主任。
1984年他获得首尔大学计算机科学与统计学士学位，1986年和1989年分别获得韩国科学技术院计算机科学硕士和博士学位。
1989年2月至1995年2月，他在韩国清州国立忠北大学计算机科学系任副教授。1995年3月，他加入韩国首尔高丽大学计算机科学与工程系，现为终身教授。2001年，他在麻省理工学院脑与认知科学系任客座教授。
李教授是国际模式识别学会IAPR（1998年）、电气和电子工程师协会IEEE（2009年）和韩国科学技术院（2009年）的会士，曾在多个专业协会担任主席或理事会理事。他是《国际文档分析与识别杂志》的创始主编，并曾担任多家国际期刊的副主编：《模式识别》、《ACM应用感知汇刊》，《IEEE情感计算汇刊》、《图像与视觉计算》、《国际模式识别与人工智能杂志》、《国际图像与图形杂志》。他也是韩国人工智能协会的创始主席。
他的研究领域包括模式识别、人工智能和脑工程。他在国际期刊和会议论文集上发表了500多篇文章，并著有10本书。
