This paper studies imitation learning in nonlinear multi-player game systems with heterogeneous control input dynamics. We propose a model-free data-driven inverse reinforcement learning (RL) algorithm for a leaner to find the cost functions of a N -player Nash expert system given the expert's states and control inputs. This allows us to address the imitation learning problem without prior knowledge of the expert's system dynamics. To achieve this, we provide a basic model-based algorithm that is built upon RL and inverse optimal control. This serves as the foundation for our final model-free inverse RL algorithm which is implemented via neural network-based value function approximators. Theoretical analysis and simulation examples verify the methods.KeywordsImitation learning • Inverse reinforcement learning • Heterogeneous multi-player games • Data-driven model-free control B Bosen Lian

Bosen Lian

Wenqian Xue

Frank L. Lewis

Control Theory and Technology

The Control Theory and Technology publishes high-quality papers on original, theoretical and experimental research and development in the area of systems and control, including all aspects of control theory and its applications. Its function is to provide a forum for domestic, as well as international, scientists and engineers in this field to exchange their knowledge and experiences. Articles for submission may be survey papers, or reviews on well established or newly emerging research topics, techniques, etc.; or regular papers which describe new well developed theoretical results or applications; or brief papers which present new techniques, concepts, perspectives, etc.Among the topics of interests areNonlinear systems and controlCyber-physical systemsIdentification and estimationOptimal control and optimizationRobust and H-infinity controlAdaptive and learning controlCooperative systemsStability and stabilizationDistributed parameter systemsHybrid systems and DEDSLarge scale systemsNetworked control systemsAutonomous systemsFault diagnosisCIMS and manufacturing systemsInformation processing systemsSystems biologyMulti-agent systemsMotion controlIntelligent controlPower systemsEnvironmental and bio-engineering systemsHuman-machine systemsIntelligent transportation systemsSocial networksEconomic systemsApplications in various fields

The journal "Control Theory and Technology" publishes high-quality papers on original theoretical and experimental research in the field of systems and control, encompassing all aspects of control theory and its applications. Its purpose is to provide a platform for both domestic and international scientists and engineers to exchange knowledge and experiences. Submissions may include survey papers or reviews on established or emerging research topics and techniques; regular papers that describe new theoretical results or applications; or brief papers presenting new techniques, concepts, and perspectives. Topics of interest include: nonlinear systems and control, cyber-physical systems, identification and estimation, optimal control and optimization, robust and H-infinity control, adaptive and learning control, cooperative systems, stability and stabilization, distributed parameter systems, hybrid systems and discrete event systems, large-scale systems, networked control systems, autonomous systems, fault diagnosis, computer integrated manufacturing systems, information processing systems, systems biology, multi-agent systems, motion control, intelligent control, power systems, environmental and bio-engineering systems, human-machine systems, intelligent transportation systems, social networks, economic systems, and applications in various fields.

《Control Theory and Technology》期刊致力于发表高质量的原创性理论和实验研究论文，涵盖系统与控制领域的各个方面，包括控制理论及其应用。期刊的功能是为国内外科学家和工程师提供一个交流知识和经验的平台。投稿的文章可以是对已有研究主题、技术等的综述论文，或是描述新发展理论结果或应用的常规论文，亦或是呈现新技术、概念、视角等的简短论文。感兴趣的主题包括：非线性系统与控制、网络物理系统、识别与估计、最优控制与优化、鲁棒控制与H-无穷控制、自适应与学习控制、协作系统、稳定性与稳定化、分布参数系统、混合系统与离散事件系统、大规模系统、网络控制系统、自治系统、故障诊断、计算机集成制造系统与制造系统、信息处理系统、系统生物学、多智能体系统、运动控制、智能控制、电力系统、环境与生物工程系统、人机系统、智能交通系统、社交网络、经济系统及各领域的应用。

Category	Quartile
计算机科学	4
计算机科学, 自动化与控制系统	4

Heterogeneous multi-player imitation learning

ivySCI AI Smartly Parses PDF, Answers Researchers' Questions, and Helps You Understand Papers in Seconds

Journal Info

Category	Quartile
AUTOMATION & CONTROL SYSTEMS	3