Timezone: »

 
Poster
Linear Contextual Bandits with Knapsacks
Shipra Agrawal · Nikhil Devanur

Wed Dec 07 09:00 AM -- 12:30 PM (PST) @ Area 5+6+7+8 #164
in Wednesday Posters »

We consider the linear contextual bandit problem with resource consumption, in addition to reward generation. In each round, the outcome of pulling an arm is a reward as well as a vector of resource consumptions. The expected values of these outcomes depend linearly on the context of that arm. The budget/capacity constraints require that the sum of these vectors doesn't exceed the budget in each dimension. The objective is once again to maximize the total reward. This problem turns out to be a common generalization of classic linear contextual bandits (linContextual), bandits with knapsacks (BwK), and the online stochastic packing problem (OSPP). We present algorithms with near-optimal regret bounds for this problem. Our bounds compare favorably to results on the unstructured version of the problem, where the relation between the contexts and the outcomes could be arbitrary, but the algorithm only competes against a fixed set of policies accessible through an optimization oracle. We combine techniques from the work on linContextual, BwK and OSPP in a nontrivial manner while also tackling new difficulties that are not present in any of these special cases.

Keywords: Bandit Algorithms · Learning Theory · Online Learning · (Other) Regression

Author Information

Shipra Agrawal (Columbia University)
Nikhil Devanur (Microsoft Research)

More from the Same Authors