Room Clearance with Feudal Hierarchical Reinforcement Learning

TL;DR

This paper introduces a hierarchical reinforcement learning approach for multi-agent room clearance tasks, demonstrating improved efficiency and behavior customization in a new simulation environment designed for military analysis.

Contribution

It presents a novel multi-agent feudal hierarchical RL framework and a new simulation environment, Gambit, for advancing RL research in complex, multi-agent military scenarios.

Findings

Hierarchical RL outperforms standard RL in multi-agent room clearance tasks.

Task decomposition enables solving complex floorplans more efficiently.

Reward prioritization influences emergent agent behaviors.

Abstract

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).