Horizon: Facebook’s Open Source Applied Reinforcement Learning Platform. In this paper we present Horizon, Facebook’s open source applied reinforcement learning (RL) platform. Horizon is an end-to-end platform designed to solve industry applied RL problems where datasets are large (millions to billions of observations), the feedback loop is slow (vs. a simulator), and experiments must be done with care because they don’t run in a simulator. Unlike other RL platforms, which are often designed for fast prototyping and experimentation, Horizon is designed with production use cases as top of mind. The platform contains workflows to train popular deep RL algorithms and includes data preprocessing, feature transformation, distributed training, counterfactual policy evaluation, optimized serving, and a model-based data understanding tool. We also showcase and describe real examples where reinforcement learning models trained with Horizon significantly outperformed and replaced supervised learning systems at Facebook.
Keywords for this software
References in zbMATH (referenced in 5 articles )
Showing results 1 to 5 of 5.
- Viappiani, Paolo; Boutilier, Craig: On the equivalence of optimal recommendation sets and myopically optimal query sets (2020)
- Xiao-Yang Liu, Hongyang Yang, Qian Chen, Runjia Zhang, Liuqing Yang, Bowen Xiao, Christina Dan Wang: FinRL: A Deep Reinforcement Learning Library for Automated Stock Trading in Quantitative Finance (2020) arXiv
- Zihan Ding, Tianyang Yu, Yanhua Huang, Hongming Zhang, Luo Mai, Hao Dong: RLzoo: A Comprehensive and Adaptive Reinforcement Learning Library (2020) arXiv
- Sergey Kolesnikov, Oleksii Hrinchuk: Catalyst.RL: A Distributed Framework for Reproducible RL Research (2019) arXiv
- Michael Schaarschmidt, Sven Mika, Kai Fricke, Eiko Yoneki: RLgraph: Modular Computation Graphs for Deep Reinforcement Learning (2018) arXiv