Neural Contextual Bandits with UCB-based Exploration
This addresses the problem of efficient exploration in contextual bandits for researchers and practitioners, offering a novel neural network-based approach with theoretical guarantees.
The paper tackles the stochastic contextual bandit problem by proposing NeuralUCB, a new algorithm that uses deep neural networks and UCB-based exploration, achieving a near-optimal regret of $ ilde O(\sqrt{T})$ and showing competitive empirical performance in benchmarks.
We study the stochastic contextual bandit problem, where the reward is generated from an unknown function with additive noise. No assumption is made about the reward function other than boundedness. We propose a new algorithm, NeuralUCB, which leverages the representation power of deep neural networks and uses a neural network-based random feature mapping to construct an upper confidence bound (UCB) of reward for efficient exploration. We prove that, under standard assumptions, NeuralUCB achieves $\tilde O(\sqrt{T})$ regret, where $T$ is the number of rounds. To the best of our knowledge, it is the first neural network-based contextual bandit algorithm with a near-optimal regret guarantee. We also show the algorithm is empirically competitive against representative baselines in a number of benchmarks.