Pursuing theoretical and algorithmic advances in decision making under uncertainty

News

TAC: Data-driven Wasserstein distributionally robust stochastic control

TAC: Data-driven Wasserstein distributionally robust stochastic control

The paper "Wasserstein distributionally robust stochastic control: A data-driven approach," authored by Insoon Yang, has been accepted for publication in the IEEE Transactions on Automatic Control. This ...
JOTA: Convex optimization approach to dynamic programming in continuous state and action spaces

JOTA: Convex optimization approach to dynamic programming in continuous state and action spaces

The paper "A convex optimization approach to dynamic programming in continuous state and action spaces," authored by Insoon Yang, has been accepted for publication in the Journal ...
ECE M.S. Thesis Award: Astghik Hakobyan's "Risk-Aware Distributionally Robust Optimization for Learning-Based Autonomous Systems"

ECE M.S. Thesis Award: Astghik Hakobyan’s “Risk-Aware Distributionally Robust Optimization for Learning-Based Autonomous Systems”

Astghik Hakobyan wins the best ECE M.S. thesis award. Her thesis, entitled "Risk-Aware Distributionally Robust Optimization for Learning-Based Autonomous Systems," has been evaluated as "excellent, very creative ...
CDC (2 papers): Wasserstein minimax control of ambiguous linear stochastic systems &  Nonconvex optimization on the Stiefel manifold

CDC (2 papers): Wasserstein minimax control of ambiguous linear stochastic systems & Nonconvex optimization on the Stiefel manifold

The papers "Minimax Control of Ambiguous Linear Stochastic Systems Using the Wasserstein Metric", and "A Stochastic Consensus Method for Nonconvex Optimization on the Stiefel Manifold" have been ...
IROS: Learning-based distributionally robust motion control with Gaussian processes

IROS: Learning-based distributionally robust motion control with Gaussian processes

The paper "Learning-based distributionally robust motion control with Gaussian processes", authored by Astghik Hakobyan, and Insoon Yang, has been accepted to the IEEE/RSJ International Conference on Intelligent ...
L4DC: Hamilton-Jacobi-Bellman Equations for Q-Learning in Continuous-Time

L4DC: Hamilton-Jacobi-Bellman Equations for Q-Learning in Continuous-Time

The paper "Hamilton-Jacobi-Bellman equations for Q-learning in continuous time", authored by Jeongho Kim, and Insoon Yang, has been accepted to the Conference on Learning for Dynamics and ...

Research Areas

Stochastic Control and Reinforcement Learning

Safe Autonomy and Risk Management

Cyber-Physical Systems