Microsoft, Redmond, WA, United States, 2017.5 - present
Senior Applied Scientist in AI & Research Group, working on robotics and ambient computing
University of California at Berkeley, EECS, Berkeley, CA, United States, 2015.4 - 2017.5
Postdoctoral Researcher in BAIR, working on hierarchical decision-making and reinforcement learning
Carnegie Mellon University, CSD, Pittsburgh, PA, United States, 2013.12 - 2015.3
Visiting Research Scholar in CORAL, working on particle filtering based multi-object tracking
University of Science and Technology of China, CSD, Hefei, Anhui, China, 2009.9 - 2014.11
Research Assistant in WrightEagle, working on hierarchical planning for large Markov decision processes
Publications
Efficient Reinforcement Learning with Hierarchies of Machines by Leveraging Internal Transitions, Aijun Bai, and Stuart Russell, Proceedings of the Twenty-Fifth International Joint Conference on Artificial Intelligence (IJCAI), Melbourne, Australia, August 19 - 25, 2017. [pdf] [bib] [code1] [code2]
Multi-Object Tracking and Identification via Particle Filtering over Sets, Aijun Bai, Reid Simmons, and Manuela Veloso, Proceedings of 20th International Conference on Information Fusion (FUSION), Xi'an, China, July 10-13, 2017. [pdf] [bib]
Concurrent Hierarchical Reinforcement Learning for RoboCup Keepaway, Aijun Bai, Stuart Russell, and Xiaoping Chen, RoboCup-2017: Robot Soccer World Cup XX, Lecture Notes in Artificial Intelligence (RoboCup), Springer Verlag, Berlin, 2017. [pdf] [bib] [code]
RoboCup 2D Soccer Simulation League: Evaluation Challenges, Mikhail Prokopenko, Peter Wang, Sebastian Marian, Aijun Bai, Xiao Li and Xiaoping Chen, RoboCup-2017: Robot Soccer World Cup XX, Lecture Notes in Artificial Intelligence (RoboCup), Springer Verlag, Berlin, 2017. [pdf] [bib]
Speeding Up HAM Learning with Internal Transitions, Aijun Bai, and Stuart Russell, The Multi-disciplinary Conference on Reinforcement Learning and Decision Making (RLDM) 2017, Ann Arbor, Michigan, USA, June 11-14, 2017. [pdf] [bib] [code1] [code2]
Markovian State and Action Abstractions for MDPs via Hierarchical MCTS, Aijun Bai, Siddharth Srivastava, and Stuart Russell, Proceedings of the 25th International Joint Conference on Artificial Intelligence (IJCAI), New York, 2016. [pdf] [bib] [slides] [poster] [code]
Online Planning for Large Markov Decision Processes with Hierarchical Decomposition, Aijun Bai, Feng Wu, and Xiaoping Chen, ACM Transactions on Intelligent Systems and Technology (ACM TIST),6(4):45:1–45:28, July 2015. [pdf] [appendix] [bib] [code]
PLEASE: Palm Leaf Search for POMDPs with Large Observation Spaces, Zongzhang Zhang, David Hsu, Wee Sun Lee, Zhan Wei Lim, and Aijun Bai, Proceedings of the 25th International Conference on Automated Planning and Scheduling (ICAPS), 2015. [pdf] [bib]
PLEASE: Palm Leaf Search for POMDPs with Large Observation Spaces, Zongzhang Zhang, David Hsu, Wee Sun Lee, Zhan Wei Lim, and Aijun Bai, Proceedings of the 8th Annual Symposium on Combinatorial Search (SoCS), 2015. [pdf] [bib]
Intention-Aware Multi-Human Tracking for Human-Robot Interaction via Particle Filtering over Sets, Aijun Bai, Reid Simmons, Manuela Veloso, and Xiaoping Chen, AAAI 2014 Fall Symposium: AI for Human-Robot Interaction (AI-HRI), Arlington, Virginia, United States, November 2014. [pdf] [bib] [video1] [video2] [code]
Thompson Sampling based Monte-Carlo Planning in POMDPs, Aijun Bai, Feng Wu, Zongzhang Zhang, and Xiaoping Chen, Proceedings of the 24th International Conference on Automated Planning and Scheduling (ICAPS), Portsmouth, New Hampshire, United States, June 2014. [pdf] [bib] [video] [slides] [code]
Bayesian Mixture Modelling and Inference based Thompson Sampling in Monte-Carlo Tree Search, Aijun Bai, Feng Wu, and Xiaoping Chen, Advances in Neural Information Processing Systems 26 (NIPS), Lake Tahoe, Nevada, United States, December 2013. [pdf] [bib] [poster] [code]
An Intelligent Service System with Multiple Robots, Qiang Lu, Guanghui Lu, Aijun Bai, Dongxiang Zhang, and Xiaoping Chen, Robot Competition of International Joint Conference on Artificial Intelligence (IJCAI), Beijing, China, 2013. [pdf] [bib]
Towards a Principled Solution to Simulated Robot Soccer, Aijun Bai, Feng Wu, and Xiaoping Chen, RoboCup-2012: Robot Soccer World Cup XVI, Lecture Notes in Artificial Intelligence (RoboCup), Vol. 7500, Springer Verlag, Berlin, 2013. [pdf] [bib] [slides] Best Paper Award Nominee at RoboCup 2012 International Symposium.
Online Planning for Large MDPs with MAXQ Decomposition (Extended Abstract), Aijun Bai, Feng Wu, and Xiaoping Chen, Proceedings of the 11th International Conference on Autonomous Agents and Multiagent Systems (AAMAS), Valencia, Spain, June 2012. [pdf] [bib] [code]
Online Planning for Large MDPs with MAXQ Decomposition, Aijun Bai, Feng Wu, and Xiaoping Chen, AAMAS 2012 Autonomous Robots and Multirobot Systems Workshop (ARMS), Valencia, Spain, June 2012. [pdf] [bib] [code]
WrightEagle and UT Austin Villa: RoboCup 2011 Simulation League Champions, Aijun Bai, Xiaoping Chen, Patrick MacAlpine, Daniel Urieli, Samuel Barrett, and Peter Stone, RoboCup-2011: Robot Soccer World Cup XV, Lecture Notes in Artificial Intelligence (RoboCup), Vol. 7416, Springer Verlag, Berlin, 2012. [pdf] [bib] [code]
Technical Reports
Markovian State and Action Abstractions for Markov Decision Processes via Hierarchical Monte Carlo Tree Search, Aijun Bai, Siddharth Srivastava, and Stuart Russell, Technical Report, University of California at Berkeley, Apr 2017. [pdf]
Posterior Sampling for Monte Carlo Planning under Uncertainty, Aijun Bai, Feng Wu, and Xiaoping Chen, Technical Report, University of California at Berkeley, Apr 2017. [pdf]
Markov Theory based Planning and Sensing under Uncertainty (in Chinese), Aijun Bai, Ph.D. Thesis of USTC, Sep 2014. [pdf] [slides]
WrightEagle 2D Soccer Simulation Team Description 2012, Aijun Bai, Haochong Zhang, Guanghui Lu, Miao Jiang, and Xiaoping Chen, RoboCup 2012, Jun 2012. [pdf]
Bridging the Gap between AI Planning and Simulation 2D: A DEC-POMDP Perspective, Feng Wu, Aijun Bai, and Xiaoping Chen, Technical Report, University of Science and Technology of China, Nov 2011 [pdf]
Report on RoboCup Federation Project “the Research Challenge”, Aijun Bai, Feng Wu, and Xiaoping Chen, The RoboCup Federation Project, Mar 2011. [pdf]
WrightEagle 2D Soccer Simulation Team Description 2010, Aijun Bai, Jiang Wang, Guanghui Lu, Yuhang Wang, Haochong Zhang, Yuanchong Zhu, Ke Shi, and Xiaoping Chen, RoboCup 2010, Jul 2010. [pdf]
Implementation of Some Key Techniques in WrightEagle 2D Soccer Simulation (in Chinese), Aijun Bai and Yunfang Tai, National University Student Innovation Program, Jun 2009. [pdf]
WrightEagle2009 2D Soccer Simulation Team Description Paper, Ke Shi, Aijun Bai, Yunfang Tai, and Xiaoping Chen, RoboCup 2009, Jun 2009. [pdf]
Research on MDP/POMDP Based Agent Planning (in Chinese), Aijun Bai, Bachelor Thesis of USTC, Jun 2009. [pdf]
WrightEagle2008 2D Soccer Simulation Team Description Paper, Ke Shi, Tengfei Liu, Aijun Bai, Wenkui Wang, Changjie Fan, and Xiaoping Chen, RoboCup 2008, Jul 2008. [pdf]
Applications of Some Intelligent Algorithms on Reversi Game (in Chinese), Aijun Bai, Undergraduates Research Program of USTC, Oct 2007. [pdf]
View Aijun Bai's profile
