[Report]Decision Making in Large Scale Incomplete Information Games

Time:2023-11-06Views:10

SpeakerGao Yang

TimeMonday, 6 November 18:00-19:00 p.m.

VenueAcademic Lecture Hall, 2nd Floor, Convention Centre


Abstract:

With the development of artificial intelligence technology, AI has been able to solve gaming problems such as chess and cards. However, for practical application scenarios such as military and finance, it still faces the problems that the game cannot be modelled, the game solution is low, and the game strategy is difficult to understand. This report analyses the technical challenges faced by large-scale games, and puts forward the reasons why classical game theory is difficult to apply in practical problems. For the current commonly used reinforcement learning solving methods, it gives a variety of accelerated solving methods, such as game similarity and migration, game approximation, distributed decision-making, etc., and also makes a preliminary discussion on the interpretability difficulties faced by multi-intelligent body reinforcement learning for solving game problems.


Biography:

Professor Gao Yang, BoD, Fellow of the Chinese Society of Artificial Intelligence, is currently Secretary and Executive Dean of the School of Intelligent Science and Technology at Nanjing University, selected for the Ministry of Education's New Century Outstanding Talent Support Programme in 2010, head of the 2019 Jiangsu Higher Education Schools Outstanding Scientific and Technological Innovation Team, and selected for the Jiangsu Provincial Military-Civilian Integration Leader Talent and Tianchi Distinguished Professor Programme in 2022. He is engaged in research and application in the fields of artificial intelligence, machine learning, and multi-intelligent body systems. As the first person in charge, he presided over one major project of National Natural Science Foundation of China (NSFC), one key project, one joint fund project, and one joint fund project of Ministry of Education of China (MOE) for equipment pre-research and development; presided over one special project of Ministry of Science and Technology (MOST) for international co-operation, one major project of Ministry of Science and Technology (MOST) for Science and Technology Innovation 2030 - "New Generation Artificial Intelligence", and one major project of Military Commission Equipment. He also presided over an international cooperation project of the Ministry of Science and Technology, a major project of the Ministry of Science and Technology Innovation 2030 - "New Generation of Artificial Intelligence", a major basic sub-project of the Ministry of Equipment Development of the Military Commissariat, and a project of the Ministry of Equipment Development of the Military Commissariat for the Innovation Special Zone. Based on the research results, he has published more than 200 academic papers in international academic journals (IEEE Trans series) and international conferences (CCF-A/B conferences), and translated the books "Statistical Reinforcement Learning" and "Algorithmic Perspectives on Machine Learning", and edited the book "Distributed Artificial Intelligence", etc. He was awarded the second prize of Jiangsu Provincial Science and Technology Award once. He was awarded the second prize of Jiangsu Provincial Science and Technology Award, the second prize of Wu Wenjun Natural Science Award of Chinese Society of Artificial Intelligence, and the Research Achievement Award of Multi-Intelligent Body Systems Specialised Group of Chinese Computer Society.