collaborators

5 papers

math.OC2025

Bayesian Risk-averse Model Predictive Control with Consistency and Stability Guarantees

Yingke Li, Yifan Lin, Enlu Zhou +1

Model Predictive Control (MPC) is a powerful framework for constrained control, but its performance and safety can be severely degraded when the prediction model is learned online…

cs.LG2025

Bayesian Risk-Sensitive Policy Optimization For MDPs With General Loss Functions

Xiaoshuang Wang, Yifan Lin, Enlu Zhou

Motivated by many application problems, we consider Markov decision processes (MDPs) with a general loss function and unknown parameters. To mitigate the epistemic uncertainty asso…

math.OC2025

Episodic Bayesian Optimal Control with Unknown Randomness Distributions

Alexander Shapiro, Enlu Zhou, Yifan Lin +1

Stochastic optimal control with unknown randomness distributions has been studied for a long time, encompassing robust control, distributionally robust control, and adaptive contro…

cs.LG2025

Reusing Historical Trajectories in Natural Policy Gradient via Importance Sampling: Convergence and Convergence Rate

Yifan Lin, Yuhao Wang, Enlu Zhou

Reinforcement learning provides a mathematical framework for learning-based control, whose success largely depends on the amount of data it can utilize. The efficient utilization o…

eess.SY2024

Approximate Bilevel Difference Convex Programming for Bayesian Risk Markov Decision Processes

Yifan Lin, Enlu Zhou

We consider infinite-horizon Markov Decision Processes where parameters, such as transition probabilities, are unknown and estimated from data. The popular distributionally robust…