k-Certainty Exploration Method: an action selector to identify the environment in reinforcement learning

DOI10.1016/S0004-3702(96)00062-8zbMath0906.68121MaRDI QIDQ1392105

Kazuteru Miyazaki, Masayuki Yamamura, Shigenobu Kobayashi

Publication date: 23 July 1998

Published in: Artificial Intelligence (Search for Journal in Brave)

zbMATH Keywords

Markov decision processesreinforcement learningpolicy iteration algorithm\(Q\)-learning\(k\)-certainty exploration method

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05)

Related Items (1)

k-Certainty Exploration Method: an action selector to identify the environment in reinforcement learning

Cites Work

• Unnamed Item
• Extended monotropic programming and duality
• k-Certainty Exploration Method: an action selector to identify the environment in reinforcement learning
• Transfer of learning by composing solutions of elemental sequential tasks
• The Complexity of Markov Decision Processes

This page was built for publication: k-Certainty Exploration Method: an action selector to identify the environment in reinforcement learning