Optimistic MLE: a generic model-based algorithm for partially observable sequential decision making

DOI10.1145/3564246.3585161WikidataQ130928901 ScholiaQ130928901MaRDI QIDQ6499235

Praneeth Netrapalli, Csaba Szepesvári, Chi Jin, Qing-hua Liu

Publication date: 8 May 2024

zbMATH Keywords

reinforcement learningPOMDPsoptimistic MLEPSRs

Mathematics Subject Classification ID

Theory of computing (68Qxx)

Cites Work

• Unnamed Item
• On the Computational Complexity of Stochastic Controller Optimization in POMDPs
• Complexity of finite-horizon Markov decision process problems
• The Complexity of Markov Decision Processes
• Bandit Algorithms
• Superhuman AI for multiplayer poker
• Learning nonsingular phylogenies and hidden Markov models
• Deep Blue

This page was built for publication: Optimistic MLE: a generic model-based algorithm for partially observable sequential decision making