Implement the DPE (Decentralized Parsimonious Exploration) algorithm from arXiv:1909.13079 #201
Labels
enhancement
I have to improve something which already works not too badly
multi-player
For multi-player bandits simulations
new algo
I have to implement a new algorithm! Yay!
The recent paper [An Optimal Algorithmin Multiplayer Multi-Armed Bandits, by Alexandre Proutière, Po-An Wang, arXiv:1909.13079] proposes an efficient algorithm for the stochastic case of multi-player MAB with collision.
The text was updated successfully, but these errors were encountered: