Nalaganje...

Optimistic Value Iteration

Markov decision processes are widely used for planning and verification in settings that combine controllable or adversarial choices with probabilistic behaviour. The standard analysis algorithm, value iteration, only provides lower bounds on infinite-horizon probabilities and rewards. Two “sound” v...

Popoln opis

Shranjeno v:
Bibliografske podrobnosti
izdano v:Computer Aided Verification
Main Authors: Hartmanns, Arnd, Kaminski, Benjamin Lucien
Format: Artigo
Jezik:Inglês
Izdano: 2020
Teme:
Online dostop:https://ncbi.nlm.nih.gov/pmc/articles/PMC7363440/
https://ncbi.nlm.nih.govhttp://dx.doi.org/10.1007/978-3-030-53291-8_26
Oznake: Označite
Brez oznak, prvi označite!