A Monte-Carlo AIXI approximation

DOI10.1613/JAIR.3125MaRDI QIDQ3081449zbMATH OpenOpenAlexDBLPWikidataFDO

Authors Joel Veness, K. S. Ng, Marcus Hutter, David Silver, William T. B. Uther

Publication date 8 March 2011

Published in Journal of Artificial Intelligence Research (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1613/jair.3125

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05) Agent technology and artificial intelligence (68T42)

Recommendations

• Scalable and efficient Bayes-adaptive reinforcement learning based on Monte-Carlo tree search
• On the computability of Solomonoff induction and AIXI
• Optimality issues of universal greedy agents with static priors
• Principles of Solomonoff Induction and AIXI
• Bayesian Reinforcement Learning with Exploration

Cited in

(6)

• On the computability of Solomonoff induction and AIXI
• Scalable and efficient Bayes-adaptive reinforcement learning based on Monte-Carlo tree search
• Universal knowledge-seeking agents
• scientific article; zbMATH DE number 6860770 (Why is no real title available?)
• A dilemma for Solomonoff prediction
• Curious coincidences and Kolmogorov complexity

Describes a project that uses

Uses Software

• POMDPS
• R-MAX

This page was built for publication: A Monte-Carlo AIXI approximation

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q3081449)