Multi-Agent Path Finding via Reinforcement Learning with Hybrid Reward

Multi-agent path finding (MAPF) aims to find a set of conflict-free paths for multiple agents so that each agent can reach its destination while optimizing a global cost. Recently, learning-based methods gain much attention due to their better real-time performance and scalability. However, most existing learning-based methods suffer from poor cooperation among agents since only local observations are used to make decisions. Meanwhile, methods that are bent on team benefits perform poorly due to a lack of individual exploration. To address this problem, this paper proposes a novel Hybrid Reward Path Finding (HRPF), which employs the global information to learn a cooperation mechanism for agents during the training, and embeds it in distributed networks to generate strategies during the execution. HRPF enforces agents to learn strategies from a new type of reward function that decomposes a complex MAPF task into a team task and individual tasks. Experiments on random obstacle grid worlds show that, HRPF performs significantly better in success rate and collision rate than state-of-the-art learning-based methods.