Modification of improved upper confidence bounds for regulating exploration in Monte-Carlo tree search

DOI10.1016/J.TCS.2016.06.034MaRDI QIDQ307787zbMATHOpenAlexFDO

Authors Yun-Ching Liu, Yoshimasa Tsuruoka

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.2016.06.034

zbMATH Keywords

multi-armed banditMonte Carlo tree searchupper confidence bounds

Mathematics Subject Classification ID

Problem solving in the context of artificial intelligence (heuristics, search strategies, etc.) (68T20) Combinatorial games (91A46) Probabilistic games; gambling (91A60)

Recommendations

• Monte Carlo tree search with robust exploration
• Towards generalizing the success of Monte-Carlo tree search beyond the game of Go
• LinUCB applied to Monte Carlo tree search
• An Analysis of UCT in Multi-player Games
• On Monte Carlo tree search and reinforcement learning

Cites work

• Asymptotically efficient adaptive allocation rules
• Finite-time analysis of the multiarmed bandit problem
• Pure exploration in multi-armed bandits problems
• Simple regret optimization in online planning for Markov decision processes
• Thompson sampling: an asymptotically optimal finite-time analysis
• UCB revisited: improved regret bounds for the stochastic multi-armed bandit problem

Cited in

(4)

• Towards generalizing the success of Monte-Carlo tree search beyond the game of Go
• Monte Carlo tree search with robust exploration
• An Analysis of UCT in Multi-player Games
• LinUCB applied to Monte Carlo tree search

This page was built for publication: Modification of improved upper confidence bounds for regulating exploration in Monte-Carlo tree search

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q307787)