Pearl
Meta's Pearl is a production-ready reinforcement learning agent package designed for real-world deployment constraints.
Ask this paper
Production-oriented design: Built for real-world environments with limited observability, sparse feedback, and high stochasticity - conditions that usually break research-oriented RL libraries.
Modular components: Offers modular policy networks, exploration strategies, offline RL, and safety constraints that can be composed for specific applications.
Research + practice: Targets both researchers building new RL agents and practitioners deploying RL in production recommender systems, ranking, and control.
Meta internal use: Reflects learnings from Meta's internal deployments, making it a rare RL library that starts from production pain rather than benchmark scores.