Pearl: A Production-ready Reinforcement Learning Agent

TL;DR

Pearl is a modular, open-source reinforcement learning framework designed specifically for production environments, addressing key challenges like exploration, partial observability, and safety, with demonstrated industry adoption and benchmarking results.

Contribution

The paper introduces Pearl, a production-ready RL software package that explicitly tackles deployment challenges and is suitable for real-world industrial applications.

Findings

Benchmarking results demonstrate Pearl's performance.

Pearl has industry adoption examples.

It addresses exploration, safety, and partial observability.

Abstract

Reinforcement learning (RL) is a versatile framework for optimizing long-term goals. Although many real-world problems can be formalized with RL, learning and deploying a performant RL policy requires a system designed to address several important challenges, including the exploration-exploitation dilemma, partial observability, dynamic action spaces, and safety concerns. While the importance of these challenges has been well recognized, existing open-source RL libraries do not explicitly address them. This paper introduces Pearl, a Production-Ready RL software package designed to embrace these challenges in a modular way. In addition to presenting benchmarking results, we also highlight examples of Pearl's ongoing industry adoption to demonstrate its advantages for production use cases. Pearl is open sourced on GitHub at github.com/facebookresearch/pearl and its official website is pearlagent.github.io.