A Reference Architecture Of Reinforcement Learning Frameworks

Abstract

The surge in reinforcement learning (RL) applications gave rise to diverse supporting technology, such as RL frameworks. However, the architectural patterns of these frameworks are inconsistent across implementations and there exists no reference architecture (RA) to form a common basis of comparison, evaluation, and integration. To address this gap, we propose an RA of RL frameworks. Through a grounded theory approach, we analyze 18 state-of-the-practice RL frameworks and, by that, we identify recurring architectural components and their relationships, and codify them in an RA. To demonstrate our RA, we reconstruct characteristic RL patterns. Finally, we identify architectural trends, e.g., commonly used components, and outline paths to improving RL frameworks.

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keyliu2026a

Related papers

• Acme: A Research Framework For Distributed Reinforcement Learning (2020)0.00
• Dopamine: A Research Framework For Deep Reinforcement Learning (2018)0.00
• A Comprehensive Survey Of Reinforcement Learning: From Algorithms To Practical Challenges (2024)0.00
• A Survey Of Reinforcement Learning Techniques: Strategies, Recent Development, And Future Directions (2020)0.00
• The AI Arena: A Framework For Distributed Multi-agent Reinforcement Learning (2021)0.00
• Integrating Distributed Architectures In Highly Modular RL Libraries (2020)0.00
• Scilab-rl: A Software Framework For Efficient Reinforcement Learning And Cognitive Modeling Research (2024)0.00
• Curriculum Learning For Reinforcement Learning Domains: A Framework And Survey (2020)0.00