From Bandits to Monte-Carlo Tree Search: The Optimistic Principle Applied to Optimization and Planning

From MaRDI portal
Publication:5168384

DOI10.1561/2200000038zbMath1296.91086OpenAlexW2073107347MaRDI QIDQ5168384

Rémi Munos

Publication date: 4 July 2014

Published in: Foundations and Trends® in Machine Learning (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1561/2200000038




Related Items (25)

Convergence rate of a rectangular subdivision-based optimization algorithm for smooth multivariate functionsContinuous-action planning for discounted infinite-horizon nonlinear optimal control with Lipschitz valuesNonasymptotic Analysis of Monte Carlo Tree SearchOptimistic optimization for model predictive control of \(\max\)-plus linear systemsOptimistic optimization for continuous nonconvex piecewise affine functionsOptimistic planning algorithms for state-constrained optimal control problemsThe aircraft runway scheduling problem: a surveyRevisiting norm optimization for multi-objective black-box problems: a finite-time analysisMulti-armed bandits with censored consumption of resourcesUnnamed ItemOptimistic planning for control of hybrid-input nonlinear systemsImproving SAT Solving Using Monte Carlo Tree Search-Based Clause LearningPlanning in hybrid relational MDPsGaussian process bandits with adaptive discretizationA unified framework for stochastic optimizationConsensus for black-box nonlinear agents using optimistic optimizationUnnamed ItemPlanning for optimal control and performance certification in nonlinear systems with controlled or uncontrolled switchesConvergence rate of a simulated annealing algorithm with noisy observationsOptimistic minimax search for noncooperative switched control with or without dwell timeOn Monte-Carlo tree search for deterministic games with alternate moves and complete informationLearning‐based iterative modular adaptive control for nonlinear systemsOnline Learning in Markov Decision Processes with Continuous ActionsMulti-objective simultaneous optimistic optimizationBenchmark and Survey of Automated Machine Learning Frameworks




This page was built for publication: From Bandits to Monte-Carlo Tree Search: The Optimistic Principle Applied to Optimization and Planning