Online Regret Bounds for Markov Decision Processes with Deterministic Transitions

DOI10.1007/978-3-540-87987-9_14zbMath1156.90456OpenAlexW2181151646MaRDI QIDQ3529915

Ronald Ortner

Publication date: 14 October 2008

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

Full work available at URL: https://doi.org/10.1007/978-3-540-87987-9_14

Mathematics Subject Classification ID

Stopping times; optimal stopping problems; gambling theory (60G40) Markov and semi-Markov decision processes (90C40)

Related Items (1)

Online regret bounds for Markov decision processes with deterministic transitions

Cites Work

• Unnamed Item
• Unnamed Item
• Asymptotically efficient adaptive allocation rules
• A characterization of the minimum cycle mean in a digraph
• Markov chain sensitivity measured by mean first passage times
• Near-optimal reinforcement learning in polynomial time
• Optimal learning and experimentation in bandit problems.
• Mixing times with applications to perturbed Markov chains
• Finding minimum cost to time ratio cycles with small integral transit times
• Pseudometrics for State Aggregation in Average Reward Markov Decision Processes
• Asymptotically efficient adaptive allocation rules for the multiarmed bandit problem with switching cost
• Optimal Adaptive Policies for Markov Decision Processes
• The Nonstochastic Multiarmed Bandit Problem
• Improved Rates for the Stochastic Continuum-Armed Bandit Problem
• Faster parametric shortest path and minimum‐balance algorithms
• Finite-time analysis of the multiarmed bandit problem

This page was built for publication: Online Regret Bounds for Markov Decision Processes with Deterministic Transitions