Slowly changing adversarial bandit algorithms are efficient for discounted MDPs

MaRDI QIDQ7017090zbMATH OpenFDO

Authors Ian A. Kash, Lev Reyzin, Zishun Yu

Publication date 6 March 2025

Full work available at URL https://proceedings.mlr.press/v237/kash24a.html

zbMATH Keywords

black-box reductiondiscounted Markov decision processesmulti-armed banditsreinforcement learning

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05) Markov and semi-Markov decision processes (90C40) Probabilistic games; gambling (91A60)

Cites work

• 10.1162/153244303768966102
• An analysis of model-based interval estimation for Markov decision processes
• scientific article; zbMATH DE number 1306865 (Why is no real title available?)
• scientific article; zbMATH DE number 7014219 (Why is no real title available?)
• Near-optimal reinforcement learning in polynomial time
• On the convergence of reinforcement learning with Monte Carlo exploring starts
• Online learning and online convex optimization
• Online Markov decision processes
• PAC Bounds for Discounted MDPs
• Regret bounds for reinforcement learning via Markov chain concentration
• Reinforcement learning. An introduction
• Revisiting the Arcade Learning Environment: Evaluation Protocols and Open Problems for General Agents
• The efficacy of pessimism in asynchronous Q-learning
• The Nonstochastic Multiarmed Bandit Problem

This page was built for publication: Slowly changing adversarial bandit algorithms are efficient for discounted MDPs

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q7017090)