Q-Mixing Network for Multi-Agent Pathfinding in Partially Observable Grid Environments
It addresses the problem of cooperative pathfinding for agents in environments with limited visibility, which is incremental as it builds on existing Q-learning methods.
The paper tackles multi-agent navigation in partially observable grid environments by using reinforcement learning with a mixing Q-network to learn cooperative policies, showing plausible results and good scalability to many agents.
In this paper, we consider the problem of multi-agent navigation in partially observable grid environments. This problem is challenging for centralized planning approaches as they, typically, rely on the full knowledge of the environment. We suggest utilizing the reinforcement learning approach when the agents, first, learn the policies that map observations to actions and then follow these policies to reach their goals. To tackle the challenge associated with learning cooperative behavior, i.e. in many cases agents need to yield to each other to accomplish a mission, we use a mixing Q-network that complements learning individual policies. In the experimental evaluation, we show that such approach leads to plausible results and scales well to large number of agents.