Title : Deep Multi-Agent Reinforcement Learning: Direct and Game-Theoretical Approaches 

Ying Wen

Abstract :
Despite the recent success of applying deep reinforcement learning (RL) algorithms on various problems in the single-agent case, it is still challenging to transfer these methods into the multi-agent RL context. The reason is that independent learning will ignore others in the environment, which breaks the theoretical guarantee of convergence. At first, this tutorial gives an overview of deep multi-agent reinforcement learning (MARL) concepts, challenges, and game theory foundations. Then, we will cover the methods of direct RL extensions in the multi-agent context, including independent learner (IL), communication-based methods, and various centralized critic methods. Finally, the tutorial will also discuss some recent trends in applying game-theoretical analysis in deep MARL, such as policy-space response oracles (PSRO) and multi-agent trust region learning (MATRL).

Biography :
Ying Wen is a tenure-track Assistant Professor in John Hopcroft Center for Computer Science at Shanghai Jiao Tong University. His research interests include reinforcement learning, multi-agent learning, game theory, and their applications in real-world scenarios. His research about multi-agent reinforcement learning has been published in top-tier international conferences, such as ICML, ICLR, IJCAI, and AAMAS. He recently obtained his Ph.D. from the Department of Computer Science at the University College London, supervised by Prof. Jun Wang of multi-agent reinforcement learning. Before that, Ying earned his MRes(Master of Research) with Distinction Honor from University College London in 2016 and B.Eng. with First Class Honor from Queen Mary, University of London and Beijing University of Posts and Tel. in 2015.