Mixed-Reality Digital Twins: Leveraging the Physical and Virtual Worlds for Hybrid Sim2Real Transition of Multi-Agent Reinforcement Learning Policies
This addresses efficiency and feasibility issues for researchers and practitioners deploying MARL in real-world vehicle systems, though it appears incremental as it builds on existing sim2real and parallelization methods.
The paper tackles the slow training and deployment challenges of multi-agent reinforcement learning for cyber-physical systems by introducing a mixed-reality digital twin framework, achieving up to 76.3% reduction in training time and a sim2real gap as low as 2.9%.
Multi-agent reinforcement learning (MARL) for cyber-physical vehicle systems usually requires a significantly long training time due to their inherent complexity. Furthermore, deploying the trained policies in the real world demands a feature-rich environment along with multiple physical embodied agents, which may not be feasible due to monetary, physical, energy, or safety constraints. This work seeks to address these pain points by presenting a mixed-reality (MR) digital twin (DT) framework capable of: (i) boosting training speeds by selectively scaling parallelized simulation workloads on-demand, and (ii) immersing the MARL policies across hybrid simulation-to-reality (sim2real) experiments. The viability and performance of the proposed framework are highlighted through two representative use cases, which cover cooperative as well as competitive classes of MARL problems. We study the effect of: (i) agent and environment parallelization on training time, and (ii) systematic domain randomization on zero-shot sim2real transfer, across both case studies. Results indicate up to 76.3% reduction in training time with the proposed parallelization scheme and sim2real gap as low as 2.9% using the proposed deployment method.