Maximin Action Identification: A New Bandit Framework for Games

15 February 2016

Papers citing "Maximin Action Identification: A New Bandit Framework for Games"

6 / 6 papers shown

Title
Sequential Learning of the Pareto Front for Multi-objective Bandits Elise Crépon Aurélien Garivier Wouter M. Koolen 52 1 0 29 Jan 2025
Learning Probably Approximately Correct Maximin Strategies in Simulation-Based Games with Infinite Strategy Spaces A. Marchesi F. Trovò N. Gatti 13 18 0 18 Nov 2019
Mixture Martingales Revisited with Applications to Sequential Tests and Confidence Intervals E. Kaufmann Wouter M. Koolen 31 117 0 28 Nov 2018
Sequential Test for the Lowest Mean: From Thompson to Murphy Sampling E. Kaufmann Wouter M. Koolen Aurélien Garivier 16 25 0 04 Jun 2018
Monte-Carlo Tree Search by Best Arm Identification E. Kaufmann Wouter M. Koolen 16 37 0 09 Jun 2017
Nearly Optimal Sampling Algorithms for Combinatorial Pure Exploration Lijie Chen Anupam Gupta Jiacheng Li Mingda Qiao Ruosong Wang 24 47 0 04 Jun 2017