Multi-Agent Reinforcement Learning Guided by Signal Temporal Logic Specifications
This work addresses the problem of reward design in multi-agent systems for researchers and practitioners, offering a novel integration of formal methods, though it is incremental as it builds on existing STL-DRL approaches.
The paper tackles the challenge of designing rewards for multi-agent reinforcement learning (MARL) by integrating Signal Temporal Logic (STL) specifications to guide reward generation, resulting in significant performance improvements and a notable increase in safety rates compared to MARL without STL guidance.
Reward design is a key component of deep reinforcement learning, yet some tasks and designer's objectives may be unnatural to define as a scalar cost function. Among the various techniques, formal methods integrated with DRL have garnered considerable attention due to their expressiveness and flexibility to define the reward and requirements for different states and actions of the agent. However, how to leverage Signal Temporal Logic (STL) to guide multi-agent reinforcement learning reward design remains unexplored. Complex interactions, heterogeneous goals and critical safety requirements in multi-agent systems make this problem even more challenging. In this paper, we propose a novel STL-guided multi-agent reinforcement learning framework. The STL requirements are designed to include both task specifications according to the objective of each agent and safety specifications, and the robustness values of the STL specifications are leveraged to generate rewards. We validate the advantages of our method through empirical studies. The experimental results demonstrate significant reward performance improvements compared to MARL without STL guidance, along with a remarkable increase in the overall safety rate of the multi-agent systems.