A Scalable and Parallelizable Digital Twin Framework for Sustainable Sim2Real Transition of Multi-Agent Reinforcement Learning Systems (2403.10996v4)

Abstract: Multi-agent reinforcement learning (MARL) systems usually require significantly long training times due to their inherent complexity. Furthermore, deploying them in the real world demands a feature-rich environment along with multiple embodied agents, which may not be feasible due to budget or space limitations, not to mention energy consumption and safety issues. This work tries to address these pain points by presenting a sustainable digital twin framework capable of accelerating MARL training by selectively scaling parallelized workloads on-demand, and transferring the trained policies from simulation to reality using minimal hardware resources. The applicability of the proposed digital twin framework is highlighted through two representative use cases, which cover cooperative as well as competitive classes of MARL problems. We study the effect of agent and environment parallelization on training time and that of systematic domain randomization on zero-shot sim2real transfer across both the case studies. Results indicate up to 76.3% reduction in training time with the proposed parallelization scheme and as low as 2.9% sim2real gap using the suggested deployment method.