A Reference Architecture of Reinforcement Learning Frameworks

Researchers propose a reference architecture for reinforcement learning frameworks after analyzing 18 state-of-the-practice implementations. The study identifies recurring architectural components and relationships to establish a common basis for comparison, evaluation, and integration across RL frameworks.

• →Reference architecture developed for reinforcement learning frameworks through grounded theory analysis of 18 implementations.
• →Study identifies recurring architectural components and relationships across diverse RL frameworks.
• →Research addresses inconsistent architectural patterns in current RL framework implementations.
• →Framework demonstrates characteristic RL patterns and identifies architectural trends.
• →Work provides foundation for improving RL framework design and integration.