Room Clearance with Feudal Hierarchical Reinforcement Learning
This work addresses coordination problems in multi-agent systems for military applications, though it is incremental as it builds on existing hierarchical RL methods.
The paper tackles the challenge of large state and action spaces in reinforcement learning for real-world military scenarios by introducing a feudal hierarchical RL method in a room clearance simulation, finding it solves non-trivial floorplans more efficiently than baseline algorithms.
Reinforcement learning (RL) is a general framework that allows systems to learn autonomously through trial-and-error interaction with their environment. In recent years combining RL with expressive, high-capacity neural network models has led to impressive performance in a diverse range of domains. However, dealing with the large state and action spaces often required for problems in the real world still remains a significant challenge. In this paper we introduce a new simulation environment, "Gambit", designed as a tool to build scenarios that can drive RL research in a direction useful for military analysis. Using this environment we focus on an abstracted and simplified room clearance scenario, where a team of blue agents have to make their way through a building and ensure that all rooms are cleared of (and remain clear) of enemy red agents. We implement a multi-agent version of feudal hierarchical RL that introduces a command hierarchy where a commander at the higher level sends orders to multiple agents at the lower level who simply have to learn to follow these orders. We find that breaking the task down in this way allows us to solve a number of non-trivial floorplans that require the coordination of multiple agents much more efficiently than the standard baseline RL algorithms we compare with. We then go on to explore how qualitatively different behaviour can emerge depending on what we prioritise in the agent's reward function (e.g. clearing the building quickly vs. prioritising rescuing civilians).