Personalization for Web-based Services using Offline Reinforcement Learning

no code implementations • 10 Feb 2021 • Pavlos Athanasios Apostolopoulos, Zehui Wang, Hanson Wang, Chad Zhou, Kittipat Virochsiri, Norm Zhou, Igor L. Markov

Large-scale Web-based services present opportunities for improving UI policies based on observed user interactions.

reinforcement-learning Reinforcement Learning (RL)

Reinforcement Learning-based Product Delivery Frequency Control

no code implementations • 20 Dec 2020 • Yang Liu, Zhengxing Chen, Kittipat Virochsiri, Juan Wang, Jiahao Wu, Feng Liang

We demonstrate statistically significant improvement in daily metrics and resource efficiency by our method in several notification applications at a scale of billions of users.

Recommendation Systems reinforcement-learning +1

Band-limited Soft Actor Critic Model

1 code implementation • 19 Jun 2020 • Miguel Campo, Zhengxing Chen, Luke Kung, Kittipat Virochsiri, Jian-Yu Wang

Soft Actor Critic (SAC) algorithms show remarkable performance in complex simulated environments.

Horizon: Facebook's Open Source Applied Reinforcement Learning Platform

2 code implementations • 1 Nov 2018 • Jason Gauci, Edoardo Conti, Yitao Liang, Kittipat Virochsiri, Yuchen He, Zachary Kaden, Vivek Narayanan, Xiaohui Ye, Zhengxing Chen, Scott Fujimoto

In this paper we present Horizon, Facebook's open source applied reinforcement learning (RL) platform.

counterfactual reinforcement-learning +1