chinganc at microsoft dot com

I am a Senior Researcher in the Reinforcement Learning team at Microsoft Research, Redmond. I am a practical theoretician, interested in developing theoretical foundations for designing principled algorithms that can efficiently tackle real-world challenges. My research is built on machine learning, optimization, and control theories. My current focus concerns learning efficiency, structural properties, and uncertainties in sequential decision making. Specific topics include reinforcement learning, imitation learning, online learning, meta learning, (large-scale) Gaussian processes, and integrated motion planning and control.

I received PhD in Robotics from Georgia Tech in 2020, where I was advised by Byron Boots at Institute for Robotics and Intelligent Machines. During my PhD study, I interned at Microsoft Research AI, Redmond, in Summer 2019, working with Alekh Agarwal and Andrey Kolobov; at Nvidia Research, Seattle, in Summer 2018, working with Nathan Ratliff and Dieter Fox.

Before Georgia Tech, I received from National Taiwan University (NTU) my M.S. in Mechanical Engineering in 2013, and double degrees of B.S. in Mechanical Engineering and B.S. in Electrical Engineering in 2011. During that period, I was advised by Han-Pang Huang, who directs NTU Robotics Laboratory. My previous research includes learning dynamical systems, force/impedance control, kernel methods, and approximation theory---with applications ranging from manipulator, grasping, exoskeleton, brain-computer interface, to humanoid.

I was fortunately awarded with Best Paper Award (OptRL Workshop @ NeurIPS 2019), Best Student Paper & Finalist to Best Systems Paper (RSS 2019), Best Paper (AISTATS 2018), Finalist to Best Systems Paper (RSS 2018), NVIDIA Graduate Fellowship, and Google PhD Fellowship (declined).

Preprints

  • X. Yan, B. Boots, C.-A. Cheng, Explaining Fast Improvement in Online Policy Optimization, arXiv:2007.02520, 2020 [pdf]

Journal/Conference Publications

2020

Selected for Spotlight Presentation (3%)

  • C.-A. Cheng, A. Kolobov, A. Agarwal, Policy Improvement via Imitation of Multiple Oracles, Conference on Neural Information Processing Systems, 2020 [pdf]

  • A. Rahimi*, A. Shaban*, C.-A. Cheng*, B. Boots, R. Hartley, Intra Order-preserving Functions for Calibration of Multi-Class Neural Networks, Conference on Neural Information Processing Systems, 2020 [pdf] (*equal contribution)

  • C.-A. Cheng, M. Mukadam, J. Issac, S. Birchfield, D. Fox, B. Boots, & N. Ratliff, RMPflow: A Geometric Framework for Generation of Multi-Task Motion Policies, IEEE Transactions on Automation Science and Engineering, 2020 (to be published) [pdf]

  • C.-A. Cheng, R. Tachet des Combes, B. Boots, & G. Gordon, A Reduction from Reinforcement Learning to No-Regret Online Learning, International Conference on Artificial Intelligence and Statistics, 2020 [pdf]

  • C.-A. Cheng*, J. Lee*, K. Goldberg, & B. Boots, Online Learning with Continuous Variations: Dynamic Regret and Reductions, International Conference on Artificial Intelligence and Statistics, 2020 [pdf] (*equal contribution)

  • B. Wingo, C.-A. Cheng, M. A. Murtaza, M. Zafar, S. Hutchinson, Extending Riemmanian Motion Policies to a Class of Underactuated Wheeled-Inverted-Pendulum Robots, International Conference on Robotics and Automation, 2020 [pdf]

2019

  • C.-A. Cheng*, X. Yan*, & B. Boots, Trajectory-wise Control Variates for Variance Reduction in Policy Gradient Methods, Conference on Robot Learning, 2019 [pdf] (*equal contribution)

  • M. Mukadam, C.-A. Cheng, D. Fox, B. Boots, & N. Ratliff, Riemannian Motion Policy Fusion through Learnable Lyapunov Function Reshaping, Conference on Robot Learning , 2019 [pdf]

  • Y. Pan, C.-A. Cheng, K. Saigol, K. Lee, X. Yan, E. Theodorou, & B. Boots Imitation Learning for Agile Autonomous Driving, The International Journal of Robotics Research, 2019 [pdf]

  • A. Li, C.-A. Cheng, B. Boots, & M. Egerstedt, Stable, Concurrent Controller Composition for Multi-Objective Robotic Tasks, IEEE Conference on Decision and Control, 2019 [pdf]

  • Z.-H. Kang, C.-A. Cheng, H.-P. Huang, A Singularity Handling Algorithm based on Operational Space Control for Six-degree-of-freedom Anthropomorphic Manipulators, International Journal of Advanced Robotic Systems, 2019 [pdf]

Best Student Paper Award & Finalist to the Best Systems Paper Award

  • N. Wagener*, C.-A. Cheng*, J. Sacks, & B. Boots, An Online Learning Approach to Model Predictive Control, Robotics: Science and Systems, 2019 [pdf] (*equal contribution)

Selected for Long Talk (5%)

  • C.-A. Cheng, X. Yan, N. Ratliff, & B. Boots, Predictor-Corrector Policy Optimization, International Conference on Machine Learning, 2019 [pdf]

  • C.-A. Cheng, X. Yan, E. Theodorou, & B. Boots, Accelerating Imitation Learning with Predictive Models, International Conference on Artificial Intelligence and Statistics, 2019 [pdf]

  • A. Shaban*, C.-A. Cheng*, N. Hatch, & B. Boots, Truncated Back-propagation for Bilevel Optimization, International Conference on Artificial Intelligence and Statistics, 2019 [pdf] (*equal contribution)

2018

  • C.-A. Cheng, M. Mukadam, J. Issac, S. Birchfield, D. Fox, B. Boots, & N. Ratliff, RMPflow: A Computational Graph for Automatic Motion Policy Generation, The 13th International Workshop on the Algorithmic Foundations of Robotics, 2018 [pdf]

  • H. Salimbeni*, C.-A. Cheng*, B. Boots, & M. Deisenroth, Orthogonally Decoupled Variational Gaussian Processes, Conference on Neural Information Processing Systems, 2018 [pdf] (*equal contribution)

Selected for Plenary Presentation (8%)

  • C.-A. Cheng, X. Yan, N. Wagener, & B. Boots, Fast Policy Learning Using Imitation and Reinforcement, Conference on Uncertainty in Artificial Intelligence, 2018 [pdf]

Finalist to the Best Systems Paper Award

  • Y. Pan, C.-A. Cheng, K. Saigol, K. Lee, X. Yan, E. Theodorou, & B. Boots, Agile Off-Road Autonomous Driving Using End-to-End Deep Imitation Learning, Robotics: Science and Systems, 2018 [pdf]

Best Paper Award

  • C.-A. Cheng, & B. Boots, Convergence of Value Aggregation for Imitation Learning, International Conference on Artificial Intelligence and Statistics, 2018 [pdf]

  • J. Molnar, C.-A. Cheng, L. Tiziani, B. Boots, & F. Hammond, Optical Sensing and Control Methods for Soft Pneumatically Actuated Robotic Manipulators, IEEE International Conference on Robotics and Automation, 2018 [pdf]

2016-2017

  • C.-A. Cheng, & B. Boots, Variational Inference for Gaussian Process Models with Linear Complexity, Advances in Neural Information Processing Systems, 2017 [pdf]

  • M. Mukadam, C.-A. Cheng, X. Yan, & B. Boots, Approximately Optimal Continuous-Time Motion Planning and Control via Probabilistic Inference, IEEE International Conference on Robotics and Automation, 2017 [pdf]

  • C.-A. Cheng, & B. Boots, Incremental Variational Sparse Gaussian Process Regression, Advances in Neural Information Processing Systems, 2016 [pdf]

  • C.-A. Cheng, & H.-P. Huang, Learn the Lagrangian: a Vector-Valued RKHS Approach to Identifying Lagrangian Systems, IEEE Transactions on Cybernetics, 2016 [pdf]

  • S.-Y. Lo, C.-A. Cheng, & H.-P. Huang, Virtual Impedance Control for Safe Human-Robot Interaction, Journal of Intelligent and Robotic Systems, 2016 [pdf]

  • C.-A. Cheng, H.-P. Huang, H.-K. Hsu, W.-Z. Lai, & C.-C. Cheng, Learning the Inverse Dynamics of Robotic Manipulators in Structured Reproducing Kernel Hilbert Space, IEEE Transactions on Cybernetics, 2016 [pdf]

2010-2015

  • C.-H. Chang, H.-P. Huang, H.-K. Hsu, & C.-A. Cheng, Humanoid Robot Push-Recovery Strategy Based on CMP Criterion and Angular Momentum Regulation, IEEE/ASME International Conference on Advanced Intelligent Machatronics, 2015 [pdf]

  • M.-B. Huang, H.-P. Huang, C.-C. Cheng, & C.-A. Cheng, Efficient Grasp Synthesis and Control Strategy for Robot Hand-Arm System, IEEE International Conference on Automation Science and Engineering, 2015 [pdf]

  • H.-P. Huang, Y.-H. Liu, W.-Z. Lin, Z.-H. Kang, C.-A. Cheng, & T.-H. Huang, Development of a P300 Brain-Machine Interface and Design of an Elastic Mechanism for a Rehabilitation Robot, International Journal of Automation and Smart Technology, 2015 [pdf]

  • C.-A. Cheng, H.-P. Huang, H.-K. Hsu, W.-Z. Lai, & C.-C. Cheng, Identifying the Inverse Dynamics of the Robot Manipulators with Structured Kernel, International Automatic Control Conference, 2013 [pdf]

  • T.-H. Huang, C.-A. Cheng, & H.-P. Huang, Self-Learning Assistive Exoskeleton with Sliding Mode Admittance Control, IEEE/RSJ International Conference on Intelligent Robots and Systems, 2013 [pdf]

  • C.-A. Cheng, T.-H. Huang, & H.-P. Huang, Bayesian Human Intention Estimator for Exoskeleton System, IEEE/ASME International Conference on Advanced Intelligent Mechatronics, 2013 [pdf]

  • T.-H. Huang, H.-P. Huang, C.-A. Cheng, J.-Y. Kuan, P.-T. Lee, & S.-Y. Huang,Design of a New Hybrid Control and Knee Orthosis for Human Walking and Rehabilitation, IEEE/RSJ International Conference on Intelligent Robots and Systems, 2012 [pdf]

  • H.-P. Huang, Y.-H. Liu, T.-H. Huang, Z.-H. Kang, W.-Z. Lin, C.-P. Wang, & C.-A. Cheng, Development of a Brain-Machine Interface for Motor Imagination Task, International Conference on Automation Technology, 2012 [pdf]

  • Y.-H. Liu, C.-A. Cheng, & H.-P. Huang, Novel Feature of the EEG Based Motor Imagery BCI Systems: Degree of Imagery, International Conference on System Science and Engineering, 2011 [pdf]

  • C.-A. Cheng, Y.-H. Liu, & H.-P. Huang, Motor Imagery Recognition for Brain-Computer Interfaces using Hilbert-Huang Transform and Effective Event-Related-Desynchronization Features, CSME National Conference, 2010 [pdf]

Workshop Papers

Best Paper Award

  • J. Lee*, C.-A. Cheng*, K. Goldberg, & B. Boots, Continuous Online Learning and New Insights to Online Imitation Learning, NeurIPS 2019 Optimization Foundations of Reinforcement Learning Workshop, 2019 [pdf] (*equal contribution)

  • X. Yan*, C.-A. Cheng*, & B. Boots, Trajectory-wise Control Variates for Variance Reduction in Policy Gradient Method, NeurIPS 2019 Optimization Foundations of Reinforcement Learning Workshop, 2019 [pdf] (*equal contribution)

  • C.-A. Cheng, X. Yan, N. Ratliff, & B. Boots, Predictor-Corrector Policy Optimization, Deep Reinforcement Learning Workshop NeurIPS, 2018 [pdf]

  • Y. Pan, C.-A. Cheng, K. Saigol, K. Lee, X. Yan, E. Theodorou, & B. Boots, Learning Deep Neural Network Control Policies for Agile Off-Road Autonomous Driving, The NIPS Deep Reinforcement Learning Symposium, 2017 [pdf]

  • C.-A. Cheng, & B. Boots, Convergence of Value Aggregation for Imitation Learning, The NIPS Deep Reinforcement Learning Symposium, 2017 [pdf]

  • C.-A. Cheng, & B. Boots, Incremental Variational Sparse Gaussian Process Regression, NIPS Workshop on Adaptive and Scalable Nonparametric Methods in Machine Learning, 2016 [pdf]

Theses

  • (PhD Thesis) C.-A. Cheng, Efficient and Principled Robot Learning: Theory and Algorithms, Georgia Institute of Technology, 2020 [pdf]

  • (Master Thesis) C.-A. Cheng, Robot Dynamics Learning and Human-Robot Interaction, National Taiwan University, 2013 [pdf]