Implement the DPE (Decentralized Parsimonious Exploration) algorithm from arXiv:1909.13079

[Naereen]

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.

• I should read it carefully,
• And implement in SMPyBandits their algorithms,
• To do my own comparison against RandTopM and MCTopM, and Selfish, and SIC-MMAB,
• And check and verify their claims. (or disprove them?),

Note that their review of the current state of the art is not complete, they don't quote my article, and they forgot the subsequent works of Avner & Mannor, August 2018 #139, Lugosi & Mehrabian, August 2018 #141, Bourse & Perchet, September 2018 #145. They only quoted the most recent paper by Boursier & Kaufmann & Perchet & Merhrabian, June 2019.