# Horizon: Facebook's Open Source Applied Reinforcement Learning Platform

arXiv: https://arxiv.org/abs/1811.00260 · HTML: https://mlsanity.com/paper/1811.00260/

## Key facts

- Cited by 48 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 1 Nov 2018.

## Built on by (most cited first, 30 of 48)

- [A Minimalist Approach to Offline Reinforcement Learning](https://mlsanity.com/paper/2106.06860/) (2021)
- [Harms from Increasingly Agentic Algorithmic Systems](https://mlsanity.com/paper/2302.10329/) (2023)
- [CORL: Research-oriented Deep Offline Reinforcement Learning Library](https://mlsanity.com/paper/2210.07105/) (2022)
- [Truthful AI: Developing and governing AI that does not lie](https://mlsanity.com/paper/2110.06674/) (2021)
- [Benchmarking Batch Deep Reinforcement Learning Algorithms](https://mlsanity.com/paper/1910.01708/) (2019)
- [TorchRL: A data-driven decision-making library for PyTorch](https://mlsanity.com/paper/2306.00577/) (2023)
- [AI Alignment with Changing and Influenceable Reward Functions](https://mlsanity.com/paper/2405.17713/) (2024)
- [Estimating and Penalizing Induced Preference Shifts in Recommender Systems](https://mlsanity.com/paper/2204.11966/) (2022)
- [Showing Your Offline Reinforcement Learning Work: Online Evaluation Budget Matters](https://mlsanity.com/paper/2110.04156/) (2021)
- [User Tampering in Reinforcement Learning Recommender Systems](https://mlsanity.com/paper/2109.04083/) (2021)
- [RecSim NG: Toward Principled Uncertainty Modeling for Recommender Ecosystems](https://mlsanity.com/paper/2103.08057/) (2021)
- [A Deep Reinforcement Learning Approach to Marginalized Importance Sampling with the Successor Representation](https://mlsanity.com/paper/2106.06854/) (2021)
- [RLOps: Development Life-cycle of Reinforcement Learning Aided Open RAN](https://mlsanity.com/paper/2111.06978/) (2021)
- [SRL: Scaling Distributed Reinforcement Learning to Over Ten Thousand Cores](https://mlsanity.com/paper/2306.16688/) (2023)
- [Monitored Markov Decision Processes](https://mlsanity.com/paper/2402.06819/) (2024)
- [Looper: An end-to-end ML platform for product decisions](https://mlsanity.com/paper/2110.07554/) (2021)
- [Pearl: A Production-ready Reinforcement Learning Agent](https://mlsanity.com/paper/2312.03814/) (2023)
- [Evaluation Beyond Task Performance: Analyzing Concepts in AlphaZero in Hex](https://mlsanity.com/paper/2211.14673/) (2022)
- [Acceleration for Deep Reinforcement Learning using Parallel and Distributed Computing: A Survey](https://mlsanity.com/paper/2411.05614/) (2024)
- [Modeling Recommender Ecosystems: Research Challenges at the Intersection of Mechanism Design, Reinforcement Learning and Generative Models](https://mlsanity.com/paper/2309.06375/) (2023)
- [Reinforcement Learning in Practice: Opportunities and Challenges](https://mlsanity.com/paper/2202.11296/) (2022)
- [SCOPE-RL: A Python Library for Offline Reinforcement Learning and Off-Policy Evaluation](https://mlsanity.com/paper/2311.18206/) (2023)
- [RL4RS: A Real-World Dataset for Reinforcement Learning based Recommender System](https://mlsanity.com/paper/2110.11073/) (2021)
- [Rule Mining over Knowledge Graphs via Reinforcement Learning](https://mlsanity.com/paper/2202.10381/) (2022)
- [Synthetic Data-Based Simulators for Recommender Systems: A Survey](https://mlsanity.com/paper/2206.11338/) (2022)
- [RetailSynth: Synthetic Data Generation for Retail AI Systems Evaluation](https://mlsanity.com/paper/2312.14095/) (2023)
- [Personalization for Web-based Services using Offline Reinforcement Learning](https://mlsanity.com/paper/2102.05612/) (2021)
- [Discovering an Aid Policy to Minimize Student Evasion Using Offline Reinforcement Learning](https://mlsanity.com/paper/2104.10258/) (2021)
- [Socialbots on Fire: Modeling Adversarial Behaviors of Socialbots via Multi-Agent Hierarchical Reinforcement Learning](https://mlsanity.com/paper/2110.10655/) (2021)
- [Human-Centric Resource Allocation for the Metaverse With Multiaccess Edge Computing](https://mlsanity.com/paper/2312.15313/) (2023)

## Abstract (arXiv)

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.