4 papers
Joint Chance Constrained Safe-Optimal Control
Niklas Schmid, Jared Miller, Tristan Zeller +3
We consider the finite-time optimal control of stochastic systems subject to a probabilistic constraint on the trajectories' safety. Such formulations are known as joint chance con…
Policy Gradient Algorithms for Robust MDPs with Non-Rectangular Uncertainty Sets
Mengmeng Li, Daniel Kuhn, Tobias Sutter
We propose policy gradient algorithms for robust infinite-horizon Markov decision processes (MDPs) with non-rectangular uncertainty sets, thereby addressing an open challenge in th…
Optimal Learning via Moderate Deviations Theory
Arnab Ganguly, Tobias Sutter
This paper proposes a statistically optimal approach for learning a function value using a confidence interval in a wide range of models, including general non-parametric estimatio…
Computing Optimal Joint Chance Constrained Control Policies
Niklas Schmid, Marta Fochesato, Sarah H. Q. Li +2
We consider the problem of optimally controlling stochastic, Markovian systems subject to joint chance constraints over a finite-time horizon. For such problems, standard Dynamic P…