2024-06-11-rickard24a.md

title	abstract	layout	series	publisher	issn	id	month	tex_title	firstpage	lastpage	page	order	cycles	bibtex_author	author	date	address	container-title	volume	genre	issued	pdf	extras
Learning robust policies for uncertain parametric Markov decision processes	Synthesising verifiably correct controllers for dynamical systems is crucial for safety-critical problems. To achieve this, it is important to account for uncertainty in a robust manner, while at the same time it is often of interest to avoid being overly conservative with the view of achieving a better cost. We propose a method for verifiably safe policy synthesis for a class of finite state models, under the presence of structural uncertainty. In particular, we consider uncertain parametric Markov decision processes (upMDPs), a special class of Markov decision processes, with parameterised transition functions, where such parameters are drawn from a (potentially) unknown distribution. Our framework leverages recent advancements in the so-called scenario approach theory, where we represent the uncertainty by means of scenarios, and provide guarantees on synthesised policies satisfying probabilistic computation tree logic (PCTL) formulae. We consider several common benchmarks/problems and compare our work to recent developments for verifying upMDPs.	inproceedings	Proceedings of Machine Learning Research	PMLR	2640-3498	rickard24a	0	Learning robust policies for uncertain parametric {M}arkov decision processes	876	889	876-889	876	false	Rickard, Luke and Abate, Alessandro and Margellos, Kostas	given family Luke Rickard given family Alessandro Abate given family Kostas Margellos	2024-06-11		Proceedings of the 6th Annual Learning for Dynamics & Control Conference	242	inproceedings	date-parts 2024 6 11	https://proceedings.mlr.press/v242/rickard24a/rickard24a.pdf