Search and explore: symbiotic policy synthesis in POMDPs

R Andriushchenko, A Bork, M Češka, S Junges… - … on Computer Aided …, 2023 - Springer
This paper marries two state-of-the-art controller synthesis methods for partially observable
Markov decision processes (POMDPs), a prominent model in sequential decision making
under uncertainty. A central issue is to find a POMDP controller—that solely decides based
on the observations seen so far—to achieve a total expected reward objective. As finding
optimal controllers is undecidable, we concentrate on synthesising good finite-state
controllers (FSCs). We do so by tightly integrating two modern, orthogonal methods for …

[PDF][PDF] Search and Explore: Symbiotic Policy Synthesis in POMDPs

S Junges, JP Katoen, F Macák - publications.rwth-aachen.de
This paper marries two state-of-the-art controller synthesis methods for partially observable
Markov decision processes (POMDPs), a prominent model in sequential decision making
under uncertainty. A central issue is to find a POMDP controller—that solely decides based
on the observations seen so far—to achieve a total expected reward objective. As finding
optimal controllers is undecidable, we concentrate on synthesising good finite-state
controllers (FSCs). We do so by tightly integrating two modern, orthogonal methods for …
以上显示的是最相近的搜索结果。 查看全部搜索结果