We study the pure exploration problem subject to a matroid constraint (Best-Basis) in a stochastic multi-armed bandit game. In a Best-Basis instance, ...
May 23, 2016 · Abstract:We study the pure exploration problem subject to a matroid constraint (Best-Basis) in a stochastic multi-armed bandit game.
Jun 23, 2016 · Pure Exploration of Multi-armed Bandit Under Matroid Constraints. June 23, 2016. 1 / 27. Page 2 . . . . . . Section .1. Introduction .2. Results.
May 25, 2016 · Abstract. We study the pure exploration problem subject to a matroid constraint (Best-Basis) in a stochastic multi-armed bandit game.
People also ask
What is the best multi-armed bandit algorithm?
What is the multi-armed bandit problem in reinforcement learning?
What is the multi-armed bandit method?
What are the advantages of multiarmed bandits?
Duration: 8:47
Posted: Jul 19, 2016
Posted: Jul 19, 2016
Aug 18, 2021 · Bibliographic details on Pure Exploration of Multi-armed Bandit Under Matroid Constraints.
Pure Exploration of Multi-armed Bandit Under Matroid Constraints · Topics · Ask This Paper · 46 Citations · 45 References · Related Papers ...
In this paper, we proposed a general framework called combinatorial pure exploration (CPE) that can handle pure exploration tasks for many complex bandit ...
Pure exploration in finitely-armed and continuous-armed bandits. Theor. Comput ... Pure exploration of multi-armed bandit under matroid constraints. In ...
Multi-armed bandit n arms. 1. each arm has an unknown reward distribution. 2. the reward distributions can be different. 3. Page 6. Multi-armed bandit n arms.