3 papers
stat.ML2024
Exploiting Exogenous Structure for Sample-Efficient Reinforcement Learning
Jia Wan, Sean R. Sinclair, Devavrat Shah +1
We study a structured class of Markov Decision Processes, known as Exo-MDPs, in which the state space is partitioned into exogenous and endogenous components. Exogenous states evol…
math.OC2024
Multi-Objective LQR with Linear Scalarization
Ali Jadbabaie, Devavrat Shah, Sean R. Sinclair
We study finite approximation of the Pareto front for the multi-objective linear quadratic regulator (LQR). Classical results characterize Pareto-optimal controllers through weight…
stat.ML2022
Unifying Epidemic Models with Mixtures
Arnab Sarker, Ali Jadbabaie, Devavrat Shah
The COVID-19 pandemic has emphasized the need for a robust understanding of epidemic models. Current models of epidemics are classified as either mechanistic or non-mechanistic: me…