Guardado en:
| Autores principales: | , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2023
|
| Materias: | |
| Acceso en línea: | https://arxiv.org/abs/2305.03784 |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866908935090339840 |
|---|---|
| author | Ban, Yikun Yan, Yuchen Banerjee, Arindam He, Jingrui |
| author_facet | Ban, Yikun Yan, Yuchen Banerjee, Arindam He, Jingrui |
| contents | In this paper, we study utilizing neural networks for the exploitation and exploration of contextual multi-armed bandits. Contextual multi-armed bandits have been studied for decades with various applications. To solve the exploitation-exploration trade-off in bandits, there are three main techniques: epsilon-greedy, Thompson Sampling (TS), and Upper Confidence Bound (UCB). In recent literature, a series of neural bandit algorithms have been proposed to adapt to the non-linear reward function, combined with TS or UCB strategies for exploration. In this paper, instead of calculating a large-deviation based statistical bound for exploration like previous methods, we propose, ``EE-Net,'' a novel neural-based exploitation and 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 the potential gains compared to the currently estimated reward for exploration. We provide an instance-based $\widetilde{\mathcal{O}}(\sqrt{T})$ regret upper bound for EE-Net and show that EE-Net outperforms related linear and neural contextual bandit baselines on real-world datasets. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2305_03784 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | Neural Exploitation and Exploration of Contextual Bandits Ban, Yikun Yan, Yuchen Banerjee, Arindam He, Jingrui Machine Learning In this paper, we study utilizing neural networks for the exploitation and exploration of contextual multi-armed bandits. Contextual multi-armed bandits have been studied for decades with various applications. To solve the exploitation-exploration trade-off in bandits, there are three main techniques: epsilon-greedy, Thompson Sampling (TS), and Upper Confidence Bound (UCB). In recent literature, a series of neural bandit algorithms have been proposed to adapt to the non-linear reward function, combined with TS or UCB strategies for exploration. In this paper, instead of calculating a large-deviation based statistical bound for exploration like previous methods, we propose, ``EE-Net,'' a novel neural-based exploitation and 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 the potential gains compared to the currently estimated reward for exploration. We provide an instance-based $\widetilde{\mathcal{O}}(\sqrt{T})$ regret upper bound for EE-Net and show that EE-Net outperforms related linear and neural contextual bandit baselines on real-world datasets. |
| title | Neural Exploitation and Exploration of Contextual Bandits |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2305.03784 |