Game Interactive Learning:A New Paradigm towards Intelligent Decision-Making

作     者：Junliang Xing Zhe Wu Zhaoke Yu Renye Yan Zhipeng Ji Pin Tao Yuanchun Shi 

作者机构：Department of Computer Science and TechnologyTsinghua UniversityBeijing 100084China Qiyuan LaboratoryBeijing 100094China 

出 版 物：《CAAI Artificial Intelligence Research》 (CAAI人工智能研究（英文）)

年 卷 期：2023年第2卷第1期

页      面：65-74页

学科分类：12[管理学] 1201[管理学-管理科学与工程(可授管理学、工学学位)] 081104[工学-模式识别与智能系统] 08[工学] 0835[工学-软件工程] 0811[工学-控制科学与工程] 0812[工学-计算机科学与技术（可授工学、理学学位）] 

主　　题：decision-making game interactive learning human-computer interaction game theory machine learning 

摘      要：Decision-making plays an essential role in various real-world systems like automatic driving,traffic dispatching,information system management,and emergency command and *** breakthroughs in computer game scenarios using deep reinforcement learning for intelligent decision-making have paved decision-making intelligence as a burgeoning research *** complex practical systems,however,factors like coupled distracting features,long-term interact links,and adversarial environments and opponents,make decision-making in practical applications challenging in modeling,computing,and *** work proposes game interactive learning,a novel paradigm as a new approach towards intelligent decision-making in complex and adversarial *** novel paradigm highlights the function and role of a human in the process of intelligent decision-making in complex *** formalizes a new learning paradigm for exchanging information and knowledge between humans and the machine *** proposed paradigm first inherits methods in game theory to model the agents and their preferences in the complex decision-making *** then optimizes the learning objectives from equilibrium analysis using reformed machine learning algorithms to compute and pursue promising decision results for *** interactions are involved when the learning process needs guidance from additional knowledge and instructions,or the human wants to understand the learning machine *** perform preliminary experimental verification of the proposed paradigm on two challenging decision-making tasks in tactical-level War-game *** results demonstrate the effectiveness of the proposed learning paradigm.