no code implementations • 23 Mar 2024 • Abhijit Mazumdar, Rafal Wisniewski, Manuela L. Bujorianu
In this paper, we present an online reinforcement learning algorithm for constrained Markov decision processes with a safety constraint.
1 code implementation • 15 Dec 2023 • Deividas Eringis, John Leth, Zheng-Hua Tan, Rafal Wisniewski, Mihaly Petreczky
In this paper, we derive a PAC-Bayes bound on the generalisation gap, in a supervised time-series setting for a special class of discrete-time non-linear dynamical systems.
no code implementations • 8 Dec 2023 • Abhijit Mazumdar, Rafal Wisniewski, Manuela L. Bujorianu
We then use an off-policy temporal difference learning method with importance sampling to learn the safety function corresponding to the given policy.
no code implementations • 30 Dec 2022 • Deividas Eringis, John Leth, Zheng-Hua Tan, Rafal Wisniewski, Mihaly Petreczky
In this paper we derive a PAC-Bayesian-Like error bound for a class of stochastic dynamical systems with inputs, namely, for linear time-invariant stochastic state-space models (stochastic LTI systems for short).
no code implementations • 16 Sep 2022 • Qiongxiu Li, Jaron Skovsted Gundersen, Katrine Tjell, Rafal Wisniewski, Mads Græsbøll Christensen
Privacy has become a major concern in machine learning.
no code implementations • 6 Sep 2021 • Deividas Eringis, John Leth, Zheng-Hua Tan, Rafal Wisniewski, Mihaly Petreczky
In this short article, we showcase the derivation of the optimal (minimum error variance) estimator, when one part of the stochastic LTI system output is not measured but is able to be predicted from the measured system outputs.
no code implementations • 23 Mar 2021 • Deividas Eringis, John Leth, Zheng-Hua Tan, Rafal Wisniewski, Alireza Fakhrizadeh Esfahani, Mihaly Petreczky
In this paper we derive a PAC-Bayesian error bound for autonomous stochastic LTI state-space models.