Reliability of internal prediction/estimation and its application. I: Adaptive action selection reflecting reliability of value function

DOI10.1016/j.neunet.2004.05.004zbMath1067.68591WikidataQ40489238 ScholiaQ40489238MaRDI QIDQ1886590

Yutaka Sakaguchi, Mitsuo Takano

Publication date: 18 November 2004

Published in: Neural Networks (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1016/j.neunet.2004.05.004

zbMATH Keywords

Reliability; Meta-learning; TD learning; Discount rate; Exploration-exploitation balance; Internal prediction; Model-free reinforcement learning; Temperature parameter

Mathematics Subject Classification ID

68T05: Learning and adaptive systems in artificial intelligence

Related Items

Reliability of internal prediction/estimation and its application. I: Adaptive action selection reflecting reliability of value function

Cites Work

• Dual-control theory. I
• The apparent conflict between estimation and control - a survey of the two-armed bandit problem
• A near-optimal polynomial time algorithm for learning in certain classes of stochastic games
• Simple statistical gradient-following algorithms for connectionist reinforcement learning
• \({\mathcal Q}\)-learning
• Mean, variance and probabilistic criteria in finite Markov decision processes: A review
• Reliability of internal prediction/estimation and its application. I: Adaptive action selection reflecting reliability of value function