Experimental analysis on Sarsa(λ) and Q(λ) with different eligibility traces strategies

DOI10.3233/IFS-2009-0416MaRDI QIDQ3632026zbMATH OpenFDO

Authors Jinsong Leng, Colin Fyfe, Lakhmi C. Jain

Publication date 23 June 2009

Published in Journal of Intelligent & Fuzzy Systems (Search for Journal in Brave)

Full work available at URL https://doi.org/10.3233/IFS-2009-0416

zbMATH Keywords

agentdecision-makingeligibility tracestemporal difference 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

• TD(λ) learning without eligibility traces: a theoretical analysis
• scientific article; zbMATH DE number 1501878
• The analysis of experimental results of reinforcement learning systems
• REINFORCEMENT LEARNING WITH GOAL-DIRECTED ELIGIBILITY TRACES
• Reinforcement learning with replacing eligibility traces

Cited in

(4)

• Semiconductor final test scheduling with Sarsa\((\lambda , k)\) algorithm
• TD(λ) learning without eligibility traces: a theoretical analysis
• scientific article; zbMATH DE number 1501878 (Why is no real title available?)
• The analysis of experimental results of reinforcement learning systems

This page was built for publication: Experimental analysis on Sarsa(λ) and Q(λ) with different eligibility traces strategies

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q3632026)