Near-optimal PAC bounds for discounted MDPs

DOI10.1016/J.TCS.2014.09.029MaRDI QIDQ465258zbMATH OpenOpenAlexWikidataFDO

Authors Tor Lattimore, Marcus Hutter

Publication date 31 October 2014

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

Full work available at URL https://doi.org/10.1016/j.tcs.2014.09.029

zbMATH Keywords

Markov decision processesreinforcement learningPAC boundssample-complexity

Mathematics Subject Classification ID

Computational learning theory (68Q32) Markov and semi-Markov decision processes (90C40)

Recommendations

• PAC Bounds for Discounted MDPs
• Minimax PAC bounds on the sample complexity of reinforcement learning with a generative model
• Reinforcement learning in finite MDPs: PAC analysis
• Near-optimal regret bounds for reinforcement learning
• Near-optimal reinforcement learning in polynomial time

Cites work

• An analysis of model-based interval estimation for Markov decision processes
• Asymptotically efficient adaptive allocation rules
• Bayesian Reinforcement Learning with Exploration
• Concentration Inequalities and Martingale Inequalities: A Survey
• Minimax PAC bounds on the sample complexity of reinforcement learning with a generative model
• Near-optimal regret bounds for reinforcement learning
• PAC Bounds for Discounted MDPs
• Reinforcement learning in finite MDPs: PAC analysis
• The sample complexity of exploration in the multi-armed bandit problem
• The variance of discounted Markov decision processes

Cited in

(10)

• Minimax PAC bounds on the sample complexity of reinforcement learning with a generative model
• Reinforcement learning in finite MDPs: PAC analysis
• Near-optimal regret bounds for reinforcement learning
• Complexity bounds for approximately solving discounted MDPs by value iterations
• scientific article; zbMATH DE number 2089367 (Why is no real title available?)
• Near-optimal reinforcement learning in polynomial time
• Extreme state aggregation beyond Markov decision processes
• Is Temporal Difference Learning Optimal? An Instance-Dependent Analysis
• Optimistic Posterior Sampling for Reinforcement Learning: Worst-Case Regret Bounds
• PAC Bounds for Discounted MDPs

This page was built for publication: Near-optimal PAC bounds for discounted MDPs

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q465258)