mlsanityData to 7 Oct 2026

Strategic Communication under Threat: Learning Information Trade-offs in Pursuit-Evasion Games

arXiv 2510.07813 ↗First posted 9 Oct 2025cs.AIcited by 0

Not on the map. Why?

Abstract (arXiv)

Adversarial environments require agents to navigate a key strategic trade-off: acquiring information enhances situational awareness, but may simultaneously expose them to threats. To investigate this tension, we formulate a PursuitEvasion-Exposure-Concealment Game (PEEC) in which a pursuer agent must decide when to communicate in order to obtain the evader's position. Each communication reveals the pursuer's location, increasing the risk of being targeted. Both agents learn their movement policies via reinforcement learning, while the pursuer additionally learns a communication policy that balances observability and risk. We propose SHADOW (Strategic-communication Hybrid Action Decision-making under partial Observation for Warfare), a multi-headed sequential reinforcement learning framework that integrates continuous navigation control, discrete communication actions, and opponent modeling for behavior prediction. Empirical evaluations show that SHADOW pursuers achieve higher success rates than six competitive baselines. Our ablation study confirms that temporal sequence modeling and opponent modeling are critical for effective decision-making. Finally, our sensitivity analysis reveals that the learned policies generalize well across varying communication risks and physical asymmetries between agents.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 19 of its 53 references that are in the map. First posted on arXiv 9 Oct 2025.

Builds on

19 of 53 references.

References · 19

  1. 2017Proximal Policy Optimization Algorithmscited by 14,441
  2. 2018Addressing Function Approximation Error in Actor-Critic Methodscited by 2,302
  3. 2021The Surprising Effectiveness of PPO in Cooperative, Multi-Agent Gamescited by 903
  4. 2020Agent Modelling under Partial Observability for Deep Reinforcement Learningcited by 56
  5. 2018Parametrized Deep Q-Networks Learning: Reinforcement Learning with Discrete-Continuous Hybrid Action Spacecited by 54
  6. 2021HyAR: Addressing Discrete-Continuous Action Reinforcement Learning via Hybrid Action Representationcited by 33
  7. 2019Multi-Pass Q-Networks for Deep Reinforcement Learning with Parameterised Action Spacescited by 22
  8. 2020Decentralized Multi-Agent Pursuit using Deep Reinforcement Learningcited by 21
  9. 2019Cooperative Team Strategies for Multi-player Perimeter-Defense Gamescited by 6
  10. 2020An Introduction to Pursuit-evasion Differential Gamescited by 6
  11. 2019MERL: Multi-Head Reinforcement Learningcited by 5
  12. 2021A Pursuit-Evasion Differential Game with Strategic Information Acquisitioncited by 4
7 more
  1. 2022Underwater Differential Game: Finite-Time Target Hunting Task with Communication Delaycited by 3
  2. 2024Multi-Robot Target Tracking with Sensing and Communication Danger Zonescited by 3
  3. 2014Common Information based Markov Perfect Equilibria for Linear-Gaussian Games with Asymmetric Informationcited by 1
  4. 2015Self-triggered Pursuit of a Single Evader with Uncertain Informationcited by 1
  5. 2017Linear Quadratic Games with Costly Measurementscited by 1
  6. 2023Efficient Communication for Pursuit-Evasion Games with Asymmetric Informationcited by 1
  7. 2024Optimal Evasion from a Sensing-Limited Pursuercited by 1

Built on by

Not cited yet.