|
Multi-armed Bandits (MAB) problem is used to get the balance of exploration and exploitation. I want to utilize this technique to solve my problem. I want to know where I can find a good performance source code about MAB. Thanks. |
|
If you're just looking at the basic bandit problem the algorithms described in Finite-time analysis of the multiarmed bandit problem are probably the ones you want. Honestly these algorithms are trivial to implement. Any halfway decent programmer should be able to code them up in a few hours at most. |
