6 papers
Large Deviations in Safety-Critical Systems with Probabilistic Initial Conditions
Aitor R. Gomez, Manuela L. Bujorianu, Rafal Wisniewski
We often rely on probabilistic measures -- e.g. event probability or expected time -- to characterize systems' safety. However, determining these quantities for extremely low-proba…
Provably Safe Reinforcement Learning for Stochastic Reach-Avoid Problems with Entropy Regularization
Abhijit Mazumdar, Rafal Wisniewski, Manuela L. Bujorianu
We consider the problem of learning the optimal policy for Markov decision processes with safety constraints. We formulate the problem in a reach-avoid setup. Our goal is to design…
Data-Driven Robust Safety Verification for Markov Decision Processes
Abhijit Mazumdar, Manuela L. Bujorianu, Rafal Wisniewski
In this paper, we propose a data-driven robust safety verification framework for stochastic dynamical systems modeled as Markov decision processes with time-varying and uncertain t…
An Online Multiobjective Policy Gradient for Long-run Average-reward Markov Decision Process
Rahul Misra, Manuela L. Bujorianu, RafaÅ Wisniewski
We propose a reinforcement learning (RL) framework for multi-objective decision-making, where the agent seeks to optimize a vector of rewards rather than a single scalar value. The…
Robust Correlated Equilibrium: Definition and Computation
Rahul Misra, RafaŠWisniewski, Carsten Skovmose Kallesøe +1
We study N-player finite games with costs perturbed due to time-varying disturbances in the underlying system and to that end, we propose the concept of Robust Correlated Equilibri…
Distributionally Robust Safety Verification for Markov Decision Processes
Abhijit Mazumdar, Yuting Hou, Rafal Wisniewski
In this paper, we propose a distributionally robust safety verification method for Markov decision processes where only an ambiguous transition kernel is available instead of the p…