Adaptive aggregation for reinforcement learning in average reward Markov decision processes

DOI10.1007/S10479-012-1064-YMaRDI QIDQ378753zbMATH OpenOpenAlexFDO

Authors Ronald Ortner

Publication date 12 November 2013

Published in Annals of Operations Research (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1007/s10479-012-1064-y

zbMATH Keywords

Markov decision processreinforcement learningregretbounded parameter MDP

Mathematics Subject Classification ID

Markov and semi-Markov decision processes (90C40)

Recommendations

• Markov decision processes with arbitrary reward processes
• A unified approach to adaptive control of average reward Markov decision processes
• Extreme state aggregation beyond Markov decision processes
• A time aggregation approach to Markov decision processes
• Online Markov decision processes

Cites work

• scientific article; zbMATH DE number 700091 (Why is no real title available?)
• Adaptive aggregation methods for infinite horizon dynamic programming
• An Adaptive Sampling Algorithm for Solving Markov Decision Processes
• An analysis of model-based interval estimation for Markov decision processes
• Approximate equivalence of Markov decision processes.
• Asymptotically efficient adaptive allocation rules
• Bisimulation metrics for continuous Markov decision processes
• Bounded Parameter Markov Decision Processes with Average Reward Criterion
• Bounded-parameter Markov decision processes
• Equivalence notions and model minimization in Markov decision processes
• Finite-time analysis of the multiarmed bandit problem
• Knows what it knows: a framework for self-aware learning
• Near-optimal regret bounds for reinforcement learning
• Optimal Adaptive Policies for Markov Decision Processes
• Optimal adaptive policies for sequential allocation problems
• Performance Loss Bounds for Approximate Value Iteration with State Aggregation
• Pseudometrics for State Aggregation in Average Reward Markov Decision Processes
• Simulation-based algorithms for Markov decision processes.

Cited in

(10)

• Pseudometrics for State Aggregation in Average Reward Markov Decision Processes
• Unsupervised basis function adaptation for reinforcement learning
• Selecting near-optimal approximate state representations in reinforcement learning
• Relative value iteration algorithm with soft state aggregation
• Adaptive Discretization in Online Reinforcement Learning
• Extreme state aggregation beyond MDPs
• Markov decision processes with arbitrary reward processes
• Extreme state aggregation beyond Markov decision processes
• Optimal learning with \textit{Q}-aggregation
• Clustering in block Markov chains

This page was built for publication: Adaptive aggregation for reinforcement learning in average reward Markov decision processes

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q378753)