Pseudometrics for State Aggregation in Average Reward Markov Decision Processes

DOI10.1007/978-3-540-75225-7_30zbMath1142.68403OpenAlexW1509780496MaRDI QIDQ3520073

Ronald Ortner

Publication date: 19 August 2008

Published in: Lecture Notes in Computer Science (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1007/978-3-540-75225-7_30

Mathematics Subject Classification ID

Computational learning theory (68Q32) Learning and adaptive systems in artificial intelligence (68T05) Markov and semi-Markov decision processes (90C40)

Related Items (5)

Extreme state aggregation beyond Markov decision processes ⋮ Adaptive aggregation for reinforcement learning in average reward Markov decision processes ⋮ Online Regret Bounds for Markov Decision Processes with Deterministic Transitions ⋮ Regret bounds for restless Markov bandits ⋮ A perturbation approach to approximate value iteration for average cost Markov decision processes with Borel spaces and bounded costs

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Equivalence notions and model minimization in Markov decision processes
• A new analysis of quasianalysis
• Linear dependence of stationary distributions in ergodic Markov decision processes
• Mixing times with applications to perturbed Markov chains
• Bisimulation Metrics for Continuous Markov Decision Processes
• Learning Theory and Kernel Machines
• Comparison of perturbation bounds for the stationary distribution of a Markov chain

This page was built for publication: Pseudometrics for State Aggregation in Average Reward Markov Decision Processes