LinUCB applied to Monte Carlo tree search

DOI10.1016/J.TCS.2016.06.035MaRDI QIDQ307792zbMATH OpenOpenAlexFDO

Authors Yusaku Mandai, Tomoyuki Kaneko

Publication date 5 September 2016

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

Full work available at URL https://doi.org/10.1016/j.tcs.2016.06.035

zbMATH Keywords

contextual banditLinUCBMCTSmulti-armed bandit problem

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05) Problem solving in the context of artificial intelligence (heuristics, search strategies, etc.) (68T20) Combinatorial games (91A46)

Recommendations

• Modification of improved upper confidence bounds for regulating exploration in Monte-Carlo tree search
• Nonasymptotic Analysis of Monte Carlo Tree Search
• On Monte Carlo tree search and reinforcement learning
• VOI-aware MCTS
• Monte Carlo tree search with robust exploration

Cites work

• An analysis of alpha-beta pruning
• Best-first minimax search
• Computer Go: An AI oriented survey
• Deep Blue
• Finite-time analysis of the multiarmed bandit problem
• Large-Scale Optimization for Evaluation Functions with Minimax Search
• Multi-armed bandits with episode context
• Regret analysis of stochastic and nonstochastic multi-armed bandit problems

Cited in

(3)

• Combinatorial multi-armed bandits for real-time strategy games
• Modification of improved upper confidence bounds for regulating exploration in Monte-Carlo tree search
• Nonasymptotic Analysis of Monte Carlo Tree Search

This page was built for publication: LinUCB applied to Monte Carlo tree search

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q307792)