Optimal and Greedy Algorithms for Multi-Armed Bandits with Many Arms.

Mohsen Bayati Nima Hamidi Ramesh Johari Khashayar Khosravi

Published in: CoRR (2020)

Keyphrases

multi armed bandits
greedy algorithms
greedy algorithm
multi armed bandit
bandit problems
dynamic programming
worst case
reinforcement learning
closed form
knapsack problem
objective function
search algorithm
multi objective