Influence-Augmented Local Simulators: A Scalable Solution for Fast Deep RL in Large Networked Systems
This addresses the scalability problem for RL practitioners working with complex, large-scale environments, though it appears incremental as it builds on existing simulator and modeling techniques.
The paper tackles the challenge of slow data acquisition in reinforcement learning for large networked systems by developing lightweight local simulators augmented with learned models of global influence, resulting in a considerable acceleration of the training process.
Learning effective policies for real-world problems is still an open challenge for the field of reinforcement learning (RL). The main limitation being the amount of data needed and the pace at which that data can be obtained. In this paper, we study how to build lightweight simulators of complicated systems that can run sufficiently fast for deep RL to be applicable. We focus on domains where agents interact with a reduced portion of a larger environment while still being affected by the global dynamics. Our method combines the use of local simulators with learned models that mimic the influence of the global system. The experiments reveal that incorporating this idea into the deep RL workflow can considerably accelerate the training process and presents several opportunities for the future.