Horizon: Facebook's Open Source Applied Reinforcement Learning Platform

by   Jason Gauci, et al.

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, and optimized serving. We also showcase real examples of where models trained with Horizon significantly outperformed and replaced supervised learning systems at Facebook.


page 1

page 2

page 3

page 4


DeepRacer: Educational Autonomous Racing Platform for Experimentation with Sim2Real Reinforcement Learning

DeepRacer is a platform for end-to-end experimentation with RL and can b...

DriverGym: Democratising Reinforcement Learning for Autonomous Driving

Despite promising progress in reinforcement learning (RL), developing al...

AndroidEnv: A Reinforcement Learning Platform for Android

We introduce AndroidEnv, an open-source platform for Reinforcement Learn...

gym-DSSAT: a crop model turned into a Reinforcement Learning environment

Addressing a real world sequential decision problem with Reinforcement L...

pymgrid: An Open-Source Python Microgrid Simulator for Applied Artificial Intelligence Research

Microgrids, self contained electrical grids that are capable of disconne...

JAX-LOB: A GPU-Accelerated limit order book simulator to unlock large scale reinforcement learning for trading

Financial exchanges across the world use limit order books (LOBs) to pro...

Secure and Scalable Data Classification

Content based data classification is an open challenge. Traditional Data...

Please sign up or login with your details

Forgot password? Click here to reset