Stochastic Control and Reinforcement Learning

Various critical decision-making problems associated with engineering and socio-technical systems are subject to uncertainties. Our group pursues theoretical and algorithmic advances in data-driven and model-based decision making in such uncertain environments.
Related Publications

Minimax control of ambiguous linear stochastic systems using the Wasserstein metric
Kihyun Kim, and Insoon Yang

Safe reinforcement learning for probabilistic reachability and safety specifications
Subin Huh, and Insoon Yang

Hamilton-Jacobi-Bellman Equations for Q-Learning in Continuous Time
Jeongho Kim, and Insoon Yang
Learning for Dynamics and Control (L4DC), 2020.

Risk-sensitive safety specifications for stochastic systems using conditional value-at-risk
Margaret P. Chapman, Jonathan P. Lacotte, Kevin M. Smith, Insoon Yang, Yuxi Han, Marco Pavone, Clare J. Tomlin

Wasserstein distributionally robust stochastic control: A data-driven approach
Insoon Yang

A convex optimization approach to dynamic programming in continuous state and action spaces
Insoon Yang

Stochastic subgradient methods for dynamic programming in continuous state and action spaces 
Sunho Jang, and Insoon Yang
IEEE Conference on Decision and Control (CDC), 2019.

On improving the robustness of reinforcement learning-based controllers using disturbance observer
Jeong Woo Kim, Hyungbo Shim, and Insoon Yang
IEEE Conference on Decision and Control (CDC), 2019.

A dynamic game approach to distributionally robust safety specifications for stochastic systems
Insoon Yang
Automatica, 2018.

Safety-aware optimal control of stochastic systems using conditional value-at-risk
Samantha Samuelson, and Insoon Yang
American Control Conference (ACC), 2018. (Extended version)

A convex optimization approach to distributionally robust Markov decision processes with Wasserstein distance
Insoon Yang
IEEE Control Systems Letters, 2017. (Selected for presentation at CDC 17)

Distributionally robust stochastic control with conic confidence sets
Insoon Yang
IEEE Conference on Decision and Control (CDC), 2017.

Optimal control of conditional value-at-risk in continuous time
Christopher W. Miller, and Insoon Yang
SIAM Journal on Control and Optimization, 2017.

Variance-constrained risk sharing in stochastic systems
Insoon Yang, Duncan S. Callaway, and Claire J. Tomlin
IEEE Transactions on Automatic Control, 2017.

Path integral formulation of stochastic optimal control with generalized costs
Insoon Yang, Matthias MorzfeldClaire J. Tomlin, and Alexandre J. Chorin
IFAC World Congress, 2014.

Dynamic contracts with partial observations: application to indirect load control 
Insoon Yang, Duncan S. Callaway, and Claire J. Tomlin
American Control Conference (ACC), 2014.