mlsanityData to 14 Oct 2026

Embedded Mean Field Reinforcement Learning for Perimeter-defense Game

arXiv 2505.14209 ↗First posted 20 May 2025cs.AIcited by 0

On the map: Deep reinforcement learning methods → RL for robot navigation and UAV control

Abstract (arXiv)

With the rapid advancement of unmanned aerial vehicles (UAVs) and missile technologies, perimeter-defense game between attackers and defenders for the protection of critical regions have become increasingly complex and strategically significant across a wide range of domains. However, existing studies predominantly focus on small-scale, simplified two-dimensional scenarios, often overlooking realistic environmental perturbations, motion dynamics, and inherent heterogeneity--factors that pose substantial challenges to real-world applicability. To bridge this gap, we investigate large-scale heterogeneous perimeter-defense game in a three-dimensional setting, incorporating realistic elements such as motion dynamics and wind fields. We derive the Nash equilibrium strategies for both attackers and defenders, characterize the victory regions, and validate our theoretical findings through extensive simulations. To tackle large-scale heterogeneous control challenges in defense strategies, we propose an Embedded Mean-Field Actor-Critic (EMFAC) framework. EMFAC leverages representation learning to enable high-level action aggregation in a mean-field manner, supporting scalable coordination among defenders. Furthermore, we introduce a lightweight agent-level attention mechanism based on reward representation, which selectively filters observations and mean-field information to enhance decision-making efficiency and accelerate convergence in large-scale tasks. Extensive simulations across varying scales demonstrate the effectiveness and adaptability of EMFAC, which outperforms established baselines in both convergence speed and overall performance. To further validate practicality, we test EMFAC in small-scale real-world experiments and conduct detailed analyses, offering deeper insights into the framework's effectiveness in complex scenarios.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in RL for robot navigation and UAV control, one of 15 directions in Deep reinforcement learning methods. Builds on 29 of its 60 references that are in the map. First posted on arXiv 20 May 2025.

Builds on

29 of 60 references.

Closest ancestors · 1

Same direction, newest first

  1. 2024Dynamic Trajectory and Power Control in Ultra-Dense UAV Networks: A Mean-Field Reinforcement Learning Approach21 Nov

Other references · 28

  1. 2017Attention Is All You Needcited by 60,361
  2. 2015Continuous control with deep reinforcement learningcited by 3,407
  3. 2018Addressing Function Approximation Error in Actor-Critic Methodscited by 2,417
  4. 2017Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environmentscited by 1,558
  5. 2018World Modelscited by 1,513
  6. 2018Recurrent World Models Facilitate Policy Evolutioncited by 785
  7. 2020Deep Reinforcement Learning for Autonomous Driving: A Surveycited by 721
  8. 2018Mean Field Multi-Agent Reinforcement Learningcited by 207
  9. 2015Deep Reinforcement Learning in Large Discrete Action Spacescited by 161
  10. 2017A Disentangled Recognition and Nonlinear Dynamics Model for Unsupervised Learningcited by 107
  11. 2019Learning Action Representations for Reinforcement Learningcited by 75
  12. 2023Heterogeneous-Agent Reinforcement Learningcited by 69
16 more
  1. 2020Plannable Approximations to MDP Homomorphisms: Equivariance under Actionscited by 61
  2. 2020Multi Type Mean Field Reinforcement Learningcited by 26
  3. 2023Maximum Entropy Heterogeneous-Agent Reinforcement Learningcited by 19
  4. 2024Decision Transformers for Wireless Communications: A New Paradigm of Resource Managementcited by 15
  5. 2022A Hierarchical Deep Reinforcement Learning Framework for 6-DOF UCAV Air-to-Air Combatcited by 10
  6. 2019Cooperative Team Strategies for Multi-player Perimeter-Defense Gamescited by 6
  7. 2023MA2CL:Masked Attentive Contrastive Learning for Multi-Agent Reinforcement Learningcited by 6
  8. 2021Defending a Perimeter from a Ground Intruder Using an Aerial Defender: Theory and Practicecited by 5
  9. 2024Age of Information Minimization using Multi-agent UAVs based on AI-Enhanced Mean Field Resource Allocationcited by 5
  10. 2020Perimeter-defense Game between Aerial Defender and Ground Intrudercited by 4
  11. 2019Perimeter-defense Game on Arbitrary Convex Shapescited by 2
  12. 2022The Role of Heterogeneity in Autonomous Perimeter Defense Problemscited by 2
  13. 2022Vision-based Perimeter Defense via Multiview Pose Estimationcited by 2
  14. 2022Learning Decentralized Strategies for a Perimeter Defense Game with Graph Neural Networkscited by 2
  15. 2020Dynamic Virtual Resource Allocation for 5G and Beyond Network Slicingcited by 1
  16. 2021Competitive Perimeter Defense on a Linecited by 1

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025Reinforcement Learning for Decision-Level Interception Prioritization in Drone Swarm Defense
  2. 2026Bench-MFG: A Benchmark Suite for Learning in Stationary Mean Field Games
  3. 2025PoolFlip: A Multi-Agent Reinforcement Learning Security Environment for Cyber Defense
  4. 2025Enhancing Aerial Combat Tactics through Hierarchical Multi-Agent Reinforcement Learning
  5. 2025From Static to Adaptive Defense: Federated Multi-Agent Deep Reinforcement Learning-Driven Moving Target Defense Against DoS Attacks in UAV Swarm Networks
  6. 2024SUB-PLAY: Adversarial Policies against Partially Observed Multi-Agent Reinforcement Learning Systems
  7. 2024Efficient and Scalable Deep Reinforcement Learning for Mean Field Control Games
  8. 2025Light Aircraft Game : Basic Implementation and training results analysis