Extreme state aggregation beyond Markov decision processes

DOI10.1016/J.TCS.2016.07.032zbMATH Open1353.68236OpenAlexW2482498454WikidataQ58012178 ScholiaQ58012178MaRDI QIDQ329613FDOQ329613

Authors Marcus Hutter 

Publication date 21 October 2016

Published in Theoretical Computer Science (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1016/j.tcs.2016.07.032

zbMATH Keywords

reinforcement learningnon-MDPstate aggregation

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05) Markov and semi-Markov decision processes (90C40)

Recommendations

• Extreme state aggregation beyond MDPs
• Selecting near-optimal approximate state representations in reinforcement learning
• Adaptive aggregation for reinforcement learning in average reward Markov decision processes
• Reinforcement learning of non-Markov decision processes
• Relative value iteration algorithm with soft state aggregation

Cites work

• scientific article; zbMATH DE number 5957269 (Why is no real title available?)
• scientific article; zbMATH DE number 700091 (Why is no real title available?)
• scientific article; zbMATH DE number 2168212 (Why is no real title available?)
• A General Approach to the Strong Law of Large Numbers
• Approximate equivalence of Markov decision processes.
• Consistency of Feature Markov Processes
• Equivalence notions and model minimization in Markov decision processes
• Extreme state aggregation beyond MDPs
• General time consistent discounting
• Near-optimal PAC bounds for discounted MDPs
• Near-optimal regret bounds for reinforcement learning
• On a general approach to the strong laws of large numbers
• Pseudometrics for State Aggregation in Average Reward Markov Decision Processes
• Reinforcement learning in finite MDPs: PAC analysis
• Universal artificial intelligence. Sequential decisions based on algorithmic probability.

Cited in

(7)

• Unsupervised basis function adaptation for reinforcement learning
• On State Aggregation to Approximate Complex Value Functions in Large-Scale Markov Decision Processes
• Selecting near-optimal approximate state representations in reinforcement learning
• Adaptive aggregation for reinforcement learning in average reward Markov decision processes
• Efficient abstraction selection in reinforcement learning
• Asymptotic Learnability of Reinforcement Problems with Arbitrary Dependence
• Extreme state aggregation beyond MDPs

This page was built for publication: Extreme state aggregation beyond Markov decision processes

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q329613)