Derrik E. Asher 1 , Anjon Basak 2 , Rolando Fernandez 1 , Piyush K. Sharma 1 , Erin G. Zaroukian 1 , Christopher D. Hsu 1 , Michael R. Dorothy 1 , Thomas Mahre 3 , Gerardo Galindo 4 , Luke Frerichs 1 , John Rogers 1 , John Fossaceca 1 Abstract Reinforcement learning (RL) approaches can illuminate emergent behaviors that facilitate coordination across teams of agents as part of a multi-agent system (MAS), which can provide windows of opportunity in various military tasks. Technologically advancing adversaries pose substantial risks to a friendly nation’s interests and resources. Superior resources alone are not enough to defeat adversaries in modern complex environments because adversaries create standoff in multiple domains against predictable military doctrine-based maneuvers. Therefore, as part of a defense strategy, friendly forces must use strategic maneuvers and disruption to gain superiority in complex multi-faceted domains such as multi-domain operations (MDO). One promising avenue for implementing strategic maneuver and disruption to gain superiority over adversaries is through coordination of MAS in future military operations. In this paper, we present overviews of prominent works in the RL domain with their strengths and weaknesses for overcoming the challenges associated with performing autonomous strategic maneuver and disruption in military contexts. Keywords Multi-Agent Systems, Reinforcement Learning, Multi-Domain Operation, Coordination, Military Scenario, Strategic Maneuver Introduction In simple terms, strategic maneuver can be interpreted as a set of agents coordinating their actions to achieve a common goal by overcoming an adversary. Disruption, which is a special case of strategic maneuver, can be represented as the inhibition of an adversary’s coordinated strategic maneuver. Therefore, the use of the terms strategic maneuver and disruption imply that there exists at least 2 opposing or adversarial sides that are in a dynamic struggle to gain superiority over each other by limiting, inhibiting or otherwise disrupting their opponent’s coordination or tactics, and imposing their own coordinated tactics. The nascent surge in the military modernization is motivated by the threat adversaries pose to a friendly nation in multiple domains (e.g., land, sea, air, cyber, electromagnetic, and space) 1–3 , which threatens 1 DEVCOM Army Research Laboratory, US, 2 Army Research Laboratory-Research Associateship Program, US 3 University of Colorado Boulder, 4 Texas A&M – Kingsville Corresponding author: Derrik E. Asher, DEVCOM Army Research Laboratory, 2800 Powder Mill Rd, Adelphi, MD 20783, US Email: derrik.e.asher.civ@army.mil Prepared using sagej.cls [Version: 2017/01/17 v1.20] arXiv:2203.09565v1 [cs.MA] 17 Mar 2022