EE-Net: Exploitation-Exploration Neural Networks in Contextual Bandits
This addresses the problem of non-linear reward functions in contextual bandits for applications like recommendation systems, offering a novel neural approach that is incremental over prior neural bandit methods.
The paper tackles the exploitation-exploration tradeoff in contextual bandits by proposing EE-Net, a neural-based exploration strategy that uses separate networks for reward estimation and adaptive exploration, achieving O(√T log T) regret and outperforming existing linear and neural baselines on real-world datasets.
In this paper, we propose a novel neural exploration strategy in contextual bandits, EE-Net, distinct from the standard UCB-based and TS-based approaches. Contextual multi-armed bandits have been studied for decades with various applications. To solve the exploitation-exploration tradeoff in bandits, there are three main techniques: epsilon-greedy, Thompson Sampling (TS), and Upper Confidence Bound (UCB). In recent literature, linear contextual bandits have adopted ridge regression to estimate the reward function and combine it with TS or UCB strategies for exploration. However, this line of works explicitly assumes the reward is based on a linear function of arm vectors, which may not be true in real-world datasets. To overcome this challenge, a series of neural bandit algorithms have been proposed, where a neural network is used to learn the underlying reward function and TS or UCB are adapted for exploration. Instead of calculating a large-deviation based statistical bound for exploration like previous methods, we propose "EE-Net", a novel neural-based exploration strategy. In addition to using a neural network (Exploitation network) to learn the reward function, EE-Net uses another neural network (Exploration network) to adaptively learn potential gains compared to the currently estimated reward for exploration. Then, a decision-maker is constructed to combine the outputs from the Exploitation and Exploration networks. We prove that EE-Net can achieve $\mathcal{O}(\sqrt{T\log T})$ regret and show that EE-Net outperforms existing linear and neural contextual bandit baselines on real-world datasets.