General Discounting Versus Average Reward

DOI10.1007/11894841_21MaRDI QIDQ3522990zbMATH OpenOpenAlexWikidataFDO

Authors Marcus Hutter

Publication date 4 September 2008

Published in Lecture Notes in Computer Science (Search for Journal in Brave)

Full work available at URL http://hdl.handle.net/1885/15029

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05)

Recommendations

• On average versus discounted reward temporal-difference learning
• General limit value in dynamic programming
• Markov decision processes: Discounted expected reward or average expected reward?
• What do discounted optima converge to!: A theory of discount rate asymptotics in economic models
• Relations between discounted models and average models for semi-Markov decision processes

Cited in

(4)

• An expected average reward criterion
• Open problems in universal induction \& intelligence
• General time consistent discounting
• On the possibility of learning in reactive environments with arbitrary dependence

This page was built for publication: General Discounting Versus Average Reward

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q3522990)