Home Abstract Materials Speakers Contact

Risk-aware Single-Agent & Multi-agent Reinforcement Learning: Algorithms and Meta-Alogrithms

AAMAS 2022 Tutorial, May 9-10, 2022

Auckland, New Zealand

Tutorial Abstract

This tutorial introduces the state-of-the-art risk-aware methodologies for autonomous systems by centering around the following questions:

  • What exactly is the risk, and what are the mathematical formulations of risk-awareness? We will introduce three risk-awareness metrics: Volatility-averseness, Worst-case robustness, and Failure-criticality.

  • How to design the risk-aware methods? Do we need to start from scratch? Or can we use some easy tweaks to turn existing risk-oblivious algorithms into risk-aware ones? We will focus on two categories: Inherently/Intrinsic risk-aware and Post-hoc/Meta-methods.

Our goal is for the audience to learn about the risk-aware models for security scenarios and exact/approximate algorithms to find solutions. The audience will also learn how concepts from behavioral risk-awareness have been applied and deployed in the context of decision-making. In addition, the audience can have a basic understanding of algorithmic groundings on reinforcement learning and multi-agent theory.

The tutorial aims at students and researchers interested in decision-making applications for safety and risk management. It should also be of interest to researchers on applied multi-agent systems research. We also hope that this tutorial will appeal to industry participants interested in applied work and to decision-making practitioners who may be interested in learning more about the specific techniques employed in this important class of decision-making.

Official information on AAMAS website.


Tutorial materials will be added here.

  • Talk slides is available here.


This tutorial will be co-offered by Bo Liu, Bo An and Yangyang Xu.

Bo Liu is a tenure-track assistant professor in the Dept. of Computer Science and Software Engineering at Auburn University. He obtained his Ph.D. from Autonomous Learning Lab at the University of Massachusetts Amherst, 2015, co-led by Drs. Sridhar Mahadevan and Andrew Barto. His primary research area covers decision-making under uncertainty, human-aided machine learning, symbolic AI, trustworthiness and interpretability in machine learning, and their numerous applications to BIGDATA, autonomous driving, and healthcare informatics. He has more than 30 publications on several notable venues in his current research, such as NIPS/NeurIPS, ICML, UAI, AAAI, IJCAI, AAMAS, JAIR IEEE-TNN, ACM TECS, etc. His research is funded by NSF, Amazon, Tencent (China), Adobe, and ETRI (South Korea). He was nominated for the 2016 ACM Doctoral Dissertation Award. He is the recipient of the UAI'2015 Facebook Best Student Paper Award, Tencent Rhio-Bird Faculty Research Award in 2017, and the Amazon (Faculty) Research Award in 2018. He is an Associate Editor of IEEE Transactions on Neural Networks and Learning Systems (IEEE-TNN), a senior member of IEEE, and a member of AAAI, ACM, and INFORMS.

Bo An is a President’s Council Chair Associate Professor at Nanyang Technological University, Singapore. He received the Ph.D. degree in Computer Science from the University of Massachusetts, Amherst. His current research interests include artificial intelligence, multiagent systems, computational game theory, reinforcement learning, and optimization. His research results have been successfully applied to many domains, including infrastructure security and e-commerce. He has published over 100 referred papers at AAMAS, IJCAI, AAAI, ICAPS, KDD, UAI, EC, WWW, ICLR, NeurIPS, ICML, JAAMAS, AIJ, and ACM/IEEE Transactions. Dr. An was the recipient of the 2010 IFAAMAS Victor Lesser Distinguished Dissertation Award, an Operational Excellence Award from the Commander, First Coast Guard District of the United States, 2012 INFORMS Daniel H. Wagner Prize for Excellence in Operations Research Practice, and 2018 Nanyang Research Award (Young Investigator). His publications won the Best Innovative Application Paper Award at AAMAS’12, the Innovative Application Award at IAAI’16, and the best paper award at DAI’20. He was invited to give an Early Career Spotlight talk at IJCAI’17. He led the team HogRider which won the 2017 Microsoft Collaborative AI Challenge. He was named to IEEE Intelligent Systems' "AI's 10 to Watch" list for 2018. He was invited to be an Advisory Committee member of IJCAI’18. He is PC Co-Chair of AAMAS’20. He is a member of the editorial board of JAIR and is the Associate Editor of AIJ, JAAMAS, IEEE Intelligent Systems, ACM TAAS, and ACM TIST. He was elected to the board of directors of IFAAMAS, a senior member of AAAI, and a distinguished member of ACM.

Yangyang Xu is now a tenure-track assistant professor in the Department of Mathematical Sciences at Rensselaer Polytechnic Institute. He received his B.S. in Computational Mathematics from Nanjing University in 2007, M.S. in Operations Research from the Chinese Academy of Sciences in 2010, and Ph.D. from the Department of Computational and Applied Mathematics at Rice University in 2014. His research interests are optimization theory and methods and their applications, such as machine learning, statistics, and signal processing. He developed optimization algorithms for compressed sensing, matrix completion, and tensor factorization and learning. His recent research focuses on first-order methods, stochastic optimization methods, and high-performance parallel computing. His research has been supported by NSF and IBM. He has published over 30 papers in prestigious journals and conference proceedings, such as Mathematical Programming, SIOPT, ICASSP, and NeurIPS. He was awarded the gold medal in the 2017 International Consortium of Chinese Mathematicians.

Contact Information

If you have any questions, comments, or suggestions. Please do not hesitate to contact (any one of) the speakers.
  • boliu@auburn.edu
  • boan@ntu.edu.sg
  • xuy21@rpi.edu