We describe Regular Decision Processes (RDPs) a model in between MDPs and POMDPs. Like in POMDPs, the effect of an action may depend on the entire history of actions and observations, but this dependence is restricted to regular functions only. This makes RDP a tractable, yet rich model, that does not hypothesize hidden state, and could possibly be useful for learning dynamic systems.
Regular decision processes: Modelling dynamic systems without using hidden variables / Brafman, R. I.; De Giacomo, G.. - 3:(2019), pp. 1844-1846. (Intervento presentato al convegno 18th International Conference on Autonomous Agents and Multiagent Systems, AAMAS 2019 tenutosi a Montreal; Canada).
Regular decision processes: Modelling dynamic systems without using hidden variables
Brafman R. I.
;De Giacomo G.
2019
Abstract
We describe Regular Decision Processes (RDPs) a model in between MDPs and POMDPs. Like in POMDPs, the effect of an action may depend on the entire history of actions and observations, but this dependence is restricted to regular functions only. This makes RDP a tractable, yet rich model, that does not hypothesize hidden state, and could possibly be useful for learning dynamic systems.| File | Dimensione | Formato | |
|---|---|---|---|
|
Brafman_Regular_2019.pdf
solo gestori archivio
Tipologia:
Versione editoriale (versione pubblicata con il layout dell'editore)
Licenza:
Tutti i diritti riservati (All rights reserved)
Dimensione
996.96 kB
Formato
Adobe PDF
|
996.96 kB | Adobe PDF | Contatta l'autore |
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
