A heuristically accelerated Q-learning algorithm based on Laplacian eigenmap

DOI10.13195/J.KZYJC.2012.1669MaRDI QIDQ2924523zbMATH OpenFDO

Authors Meiqiang Zhu, Yuhu Cheng, Xuesong Wang, Ming Li, Qian Zhang

Publication date 3 November 2014

Published in Control and Decision (Search for Journal in Brave)

Full work available at URL https://doi.org/10.13195/J.KZYJC.2012.1669

zbMATH Keywords

heuristic policy selectionLaplacian eigenmapQ-learningreinforcement learning

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05) Problem solving in the context of artificial intelligence (heuristics, search strategies, etc.) (68T20)

Recommendations

• Heuristically accelerated Q-learning: A new approach to speed up reinforcement learning
• Accelerating autonomous learning by using heuristic selection of actions
• Heuristically accelerated reinforcement learning: theoretical and experimental results
• A Hybrid Transfer Algorithm for Reinforcement Learning Based on Spectral Method
• Policy iteration reinforcement learning based on geodesic Gaussian basis defined on a state-action graph

Cited in

(2)

• Heuristically accelerated reinforcement learning: theoretical and experimental results
• Heuristically accelerated Q-learning: A new approach to speed up reinforcement learning

This page was built for publication: A heuristically accelerated Q-learning algorithm based on Laplacian eigenmap

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2924523)