An <i>ϵ</i>-Greedy Multiarmed Bandit Approach to Markov Decision Processes

We present REGA, a new adaptive-sampling-based algorithm for the control of finite-horizon Markov decision processes (MDPs) with very large state spaces and small action spaces. We apply a variant of the <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mi...

Full beskrivning

Bibliografiska uppgifter

Huvudupphov:	Isa Muqattash, Jiaqiao Hu
Materialtyp:	Artigo
Språk:	Inglês
Utgiven:	MDPI AG 2023-01-01
Serie:	Stats
Ämnen:	multiarmed bandits epsilon-greedy method Markov decision process (MDP) sampling optimization under uncertainties
Länkar:	https://www.mdpi.com/2571-905X/6/1/6
Taggar:	Lägg till en tagg Inga taggar, Lägg till första taggen!