Multi-Agent Coordination Profiles through State Space Perturbations

Asher, Derrik E.; Garber-Barron, Michael; Rodriguez, Sebastian S.; Zaroukian, Erin; Waytowich, Nicholas R.

doi:10.1109/csci49370.2019.00051

Cited by 6 publications

(5 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Asher et al 37 proposed the adoption of militarily relevant tactics to a simulated predator-prey pursuit task that allowed for teams of deep RL agents to engage in various tactics through capability modifications such as decoys, traps, and camouflage. Furthermore, this research group has introduced methods for measuring coordination [38][39][40] toward a framework for integrating AI agents into mixed soldier-agent teams. 41,42 With respect to simulators built using existing game engines, Fu et al 43 applied deep RL to the C2 of air defense operations.…”

Section: Background and Related Workmentioning

confidence: 99%

On games and simulators as a platform for development of artificial intelligence for command and control

Goecks

Waytowich

Asher

et al. 2022

Journal of Defense Modeling & Simulation

View full text Add to dashboard Cite

Games and simulators can be a valuable platform to execute complex multi-agent, multiplayer, imperfect information scenarios with significant parallels to military applications: multiple participants manage resources and make decisions that command assets to secure specific areas of a map or neutralize opposing forces. These characteristics have attracted the artificial intelligence (AI) community by supporting development of algorithms with complex benchmarks and the capability to rapidly iterate over new ideas. The success of AI algorithms in real-time strategy games such as StarCraft II has also attracted the attention of the military research community aiming to explore similar techniques in military counterpart scenarios. Aiming to bridge the connection between games and military applications, this work discusses past and current efforts on how games and simulators, together with the AI algorithms, have been adapted to simulate certain aspects of military missions and how they might impact the future battlefield. This paper also investigates how advances in virtual reality and visual augmentation systems open new possibilities in human interfaces with gaming platforms and their military parallels.

show abstract

Section: Background and Related Workmentioning

confidence: 99%

On games and simulators as a platform for development of artificial intelligence for command and control

Goecks

Waytowich

Asher

et al. 2022

Journal of Defense Modeling & Simulation

View full text Add to dashboard Cite

show abstract

“…Coordination is typically ill-defined in multi-agent tasks and is often used to indicate that a group of agents has performed successfully in some cooperative task domain. In prior work, various novel methods were developed and employed to measure the interdependence between agent actions while performing cooperative tasks, to confirm that these agents had in fact learned to coordinate [16][17][18][19][20][21][22][23] . The confirmation of coordination is a precursor to establishing that a MAS is capable of working with its partners instead of simply taking actions that result in some measure of optimality.…”

Section: Challengesmentioning

confidence: 99%

Strategic Maneuver and Disruption with Reinforcement Learning Approaches for Multi-Agent Coordination

Asher,

Basak,

Fernandez

et al. 2022

Preprint

View full text Add to dashboard Cite

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.

show abstract

“…In prior work, various novel methods were developed and employed to measure the interdependence between agent actions while performing cooperative tasks, to confirm that these agents had in fact learned to coordinate. [16][17][18][19][20][21][22][23] The confirmation of coordination is a precursor to establishing that an MAS is capable of working with its partners instead of simply taking actions that result in some measure of optimality. Whereas optimal behavior may be desirable in some circumstances, an agent that is simply acting optimal may result in catastrophic losses on a battlefield if the Mission has changed in some unforeseen way.…”

Section: Challengesmentioning

confidence: 99%

Strategic maneuver and disruption with reinforcement learning approaches for multi-agent coordination

Asher

Basak

Fernández

et al. 2022

Journal of Defense Modeling & Simulation

View full text Add to dashboard Cite

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 (MDOs). 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.

show abstract

Multi-Agent Coordination Profiles through State Space Perturbations

Cited by 6 publications

References 10 publications

On games and simulators as a platform for development of artificial intelligence for command and control

On games and simulators as a platform for development of artificial intelligence for command and control

Strategic Maneuver and Disruption with Reinforcement Learning Approaches for Multi-Agent Coordination

Strategic maneuver and disruption with reinforcement learning approaches for multi-agent coordination

Contact Info

Product

Resources

About