Off-policy linear temporal difference learning algorithms with a generalized oblique projection

DOI10.13232/J.CNKI.JNJU.2017.06.007MaRDI QIDQ3175278zbMATH OpenFDO

Authors Yushuang Wu, Jingwen Ma, Xingguo Chen, Xiao-Yu Chen

Publication date 18 July 2018

Full work available at URL https://doi.org/10.13232/J.CNKI.JNJU.2017.06.007

zbMATH Keywords

linear function approximationoblique projectionoff-policyreinforcement learningtemporal difference learning

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05)

Recommendations

• Off-policy learning with eligibility traces: a survey
• \(\text{Q}(\lambda)\) with off-policy corrections
• Proximal gradient temporal difference learning: stable reinforcement learning with polynomial sample complexity

Cited in

(4)

• Off-policy learning with eligibility traces: a survey
• Proximal gradient temporal difference learning: stable reinforcement learning with polynomial sample complexity
• Efficiently Breaking the Curse of Horizon in Off-Policy Evaluation with Double Reinforcement Learning
• Gradient temporal-difference learning for off-policy evaluation using emphatic weightings

This page was built for publication: Off-policy linear temporal difference learning algorithms with a generalized oblique projection

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q3175278)