Structured best arm identification with fixed confidence

MaRDI QIDQ4645671zbMATH OpenFDO

Authors

Publication date 10 January 2019

Full work available at URL https://arxiv.org/abs/1706.05198, http://proceedings.mlr.press/v76/huang17a.html

zbMATH Keywords

best arm identificationgame tree searchminimax searchMonte Carlo tree searchmulti-armed banditsstructured environments

Mathematics Subject Classification ID

Minimax problems in mathematical programming (90C47) Probabilistic games; gambling (91A60)

Recommendations

• On the complexity of best-arm identification in multi-armed bandit models
• Pure exploration in infinitely-armed bandit models with fixed-confidence
• From bandits to Monte-Carlo tree search: the optimistic principle applied to optimization and planning
• Best-first fixed-depth minimax algorithms
• Best-first minimax search

This page was built for publication: Structured best arm identification with fixed confidence

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q4645671)