Analytical mean squared error curves for temporal difference learning

DOI10.1023/A:1007495401240zbMath0901.68168OpenAlexW1716849269MaRDI QIDQ1266172

Peter Dayan, Satinder Pal Singh

Publication date: 7 September 1998

Published in: Machine Learning (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1023/a:1007495401240

zbMATH Keywords

reinforcement learningMarkov reward processes

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05)

Related Items

Automated Reinforcement Learning (AutoRL): A Survey and Open Problems, The optimal unbiased value estimator and its relation to LSTD, TD and MC, Temporal-difference search in Computer Go, Q( $$\lambda $$ ) with Off-Policy Corrections