Transferring knowledge as heuristics in reinforcement learning: a case-based approach

DOI10.1016/J.ARTINT.2015.05.008MaRDI QIDQ898746zbMATH OpenOpenAlexWikidataFDO

Authors Reinaldo A. C. Bianchi, Luiz A. jun. Celiberto, Jackson P. Matsuura, Paulo E. Santos, Ramon López de Mántaras

Publication date 18 December 2015

Published in Artificial Intelligence (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1016/j.artint.2015.05.008

zbMATH Keywords

transfer learningreinforcement learningcase-based reasoning

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05)

Recommendations

• Transfer learning via advice taking
• Transfer of experience between reinforcement learning environments with progressive difficulty
• scientific article; zbMATH DE number 1753136
• Transfer in variable-reward hierarchical reinforcement learning
• Transfer learning via inter-task mappings for temporal difference learning

Cites work

• [article; zbMATH DE number 2038829 (Why is no real title available?)]
• [article; zbMATH DE number 1753136 (Why is no real title available?)]
• [article; zbMATH DE number 886124 (Why is no real title available?)]
• A New Approach to Manipulator Control: The Cerebellar Model Articulation Controller (CMAC)
• Accelerating autonomous learning by using heuristic selection of actions
• Advances in Artificial Intelligence – SBIA 2004
• Case-based multiagent reinforcement learning: cases as heuristics for selection of actions
• Heuristically accelerated reinforcement learning: theoretical and experimental results
• Learning representations by back-propagating errors
• Mersenne twister
• Similarity and distance in case based reasoning
• Similarity and metrics in case-based reasoning
• Transfer learning for reinforcement learning domains: a survey

Cited in

(4)

• Transfer learning via advice taking
• Qualitative case-based reasoning and learning
• Machine Learning: ECML 2003
• Disassembly line optimization with reinforcement learning

Describes a project that uses

Uses Software

• MersenneTwister
• RL-Glue
• Mountain Car 3D
• SimSpark

This page was built for publication: Transferring knowledge as heuristics in reinforcement learning: a case-based approach

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q898746)