Learning to control by neural networks using eligibility traces

DOI10.7641/CTA.2015.40367MaRDI QIDQ2992499zbMATH OpenFDO

Authors

Publication date 10 August 2016

zbMATH Keywords

neural networksreinforcement learninggradient descent methodeligibility traces

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05) Neural networks for/in biological studies, artificial life and related topics (92B20) Stochastic learning and adaptive control (93E35)

Recommendations

• Reinforcement learning with replacing eligibility traces
• Reinforcement learning with replacing eligibility traces
• scientific article; zbMATH DE number 409559
• Learning optimal control in deterministic systems
• REINFORCEMENT LEARNING WITH GOAL-DIRECTED ELIGIBILITY TRACES

Cited in

(2)

• Advances in Neural Networks – ISNN 2005
• REINFORCEMENT LEARNING WITH GOAL-DIRECTED ELIGIBILITY TRACES

This page was built for publication: Learning to control by neural networks using eligibility traces

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2992499)