Re:Reinforcement Learning – Bandit Problems
by joshuamorton on Monday May 07, 2018 @01:44PM
(#17014740)
>because I feel like that adds state dependent on t to the bandit scenario, which then feels more like MDP.
Yeah this was sort of exactly the issue I was running into. I can't justify it to myself without essentially saying "this is just an MDP in disguise", which maybe is the right way to do it. I'm pretty sure you can define a k-armed bandit as an MDP on a single state, where each action corresponds to a machine, and all actions return you to the single state.
So maybe that is the right motivation. But reversing that "an MDP is just a k-armed bandit problem where sometimes playing a machine breaks it and forces you to play other machines, which can impact how quickly the casino fixes your first machine..." feels forced.
Yeah this was sort of exactly the issue I was running into. I can't justify it to myself without essentially saying "this is just an MDP in disguise", which maybe is the right way to do it. I'm pretty sure you can define a k-armed bandit as an MDP on a single state, where each action corresponds to a machine, and all actions return you to the single state.
So maybe that is the right motivation. But reversing that "an MDP is just a k-armed bandit problem where sometimes playing a machine breaks it and forces you to play other machines, which can impact how quickly the casino fixes your first machine..." feels forced.
All that said, its a good article :)