Pursuing theoretical and algorithmic advances in data-driven decision making under uncertainty

News

[NeurIPS] Improved regret analysis for variance-adaptive linear bandits

[NeurIPS] Improved regret analysis for variance-adaptive linear bandits

The paper "Improved regret analysis for variance-adaptive linear bandits and horizon-free linear mixture MDPs," co-authored by Yeoneung Kim and Kwang-Sung Jun, has been accepted to Neural Information ...
[T-RO] Distributionally robust risk map for learning-based motion planning and control

[T-RO] Distributionally robust risk map for learning-based motion planning and control

The paper "Distributionally robust risk map for learning-based motion planning and control: A semidefinite programming approach" has been accepted for publication in the IEEE Transactions on Robotics ...
[CDC 2 papers] Distributionally robust partially observable control, Distributionally robust unit commitment

[CDC 2 papers] Distributionally robust partially observable control, Distributionally robust unit commitment

The papers "Wasserstein distributionally robust control of partially observable linear systems: Tractable approximation and performance guarantee" and "On affine policies for Wasserstein distributionally robust unit commitment" have ...
[RA-L & IROS] Infusing MPC into meta-RL

[RA-L & IROS] Infusing MPC into meta-RL

The paper "Infusing model predictive control into meta-reinforcement learning for mobile robots in dynamic environments" has been accepted to IEEE Robotics and Automation Letters (RA-L) and 2022 ...
[ICML] Accelerated gradient methods for geodesically convex optimization

[ICML] Accelerated gradient methods for geodesically convex optimization

The paper "Accelerated gradient methods for geodesically convex optimization: Tractable algorithms and convergence analysis" has been accepted to the International Conference on Machine Learning (ICML). Accelerated gradient ...
[TAC] Maximum entropy optimal control in continuous time

[TAC] Maximum entropy optimal control in continuous time

The paper "Maximum entropy optimal control of continuous-time dynamical systems" has been accepted for publication in the IEEE Transactions on Automatic Control. Maximum entropy optimal control of ...

Research Areas

Stochastic Control and Reinforcement Learning

Optimization for Machine Learning

Safe Autonomy and Risk Management