Apr 5, 2023 · In this work, we apply upper confidence bound (UCB) to our large scale short video recommender system and present a test framework for the production bandit ...

We show through large-scale production recommender system experiments and in-depth analysis that our bandit agent design improves personalization for the ...

Evaluating online bandit exploration in large-scale recommender system ... Optimism based exploration in large-scale recommender systems. H Guo, R Naeff ...

Jul 30, 2023 · Beyond MAB, exploration and long-term value optimiza- tion are also critical in reinforcement learning based recommender systems [7, 8, 33, 36].

Missing: Optimism Exploration

In this work, we present a novel design of production bandit learning life-cycle for recommender systems, along with a novel set of metrics to measure their ...

Bandits are a good fit as they can incrementally update with new data and adaptively focus on items with higher reward.

Evaluating Online Bandit Exploration In Large-Scale Recommender System ... Optimism Based Exploration in Large-Scale Recommender Systems · Hongbo Guo ...

翻译：基于贝叶斯赌博算法的推荐系统设计在学术界受到广泛关注，但其中存在一些瓶颈，导致很难将其应用于生产上。导致这些瓶颈的主要原因包括多任务推荐系统的可扩展性和A/B ...