A sparse sampling algorithm for near-optimal planning in large Markov decision processes

DOI10.1023/A:1017932429737zbMath1014.68150MaRDI QIDQ1604816

Michael Kearns, Andrew Y. Ng, Yishay Mansour

Publication date: 8 July 2002

Published in: Machine Learning (Search for Journal in Brave)

zbMATH Keywords

Markov decision processes

Mathematics Subject Classification ID

Problem solving in the context of artificial intelligence (heuristics, search strategies, etc.) (68T20)

Related Items (18)

Safe learning for near-optimal scheduling ⋮ Nonasymptotic Analysis of Monte Carlo Tree Search ⋮ Testing probabilistic equivalence through reinforcement learning ⋮ A variable neighborhood search based algorithm for finite-horizon Markov decision processes ⋮ Reducing reinforcement learning to KWIK online regression ⋮ Knows what it knows: a framework for self-aware learning ⋮ From Reinforcement Learning to Deep Reinforcement Learning: An Overview ⋮ Planning in hybrid relational MDPs ⋮ Simulation-based search ⋮ Solving for Best Responses and Equilibria in Extensive-Form Games with Reinforcement Learning Methods ⋮ Provably Near-Optimal Approximation Schemes for Implicit Stochastic and Sample-Based Dynamic Programs ⋮ An anytime multistep anticipatory algorithm for online stochastic combinatorial optimization ⋮ Unnamed Item ⋮ APPSSAT: Approximate probabilistic planning using stochastic satisfiability ⋮ Variance Reduced Value Iteration and Faster Algorithms for Solving Markov Decision Processes ⋮ Learning and planning in partially observable environments without prior domain knowledge ⋮ Unnamed Item ⋮ Solving factored MDPs using non-homogeneous partitions

This page was built for publication: A sparse sampling algorithm for near-optimal planning in large Markov decision processes