# Decentralized Multi-Agent Pursuit using Deep Reinforcement Learning

arXiv: https://arxiv.org/abs/2010.08193 · HTML: https://mlsanity.com/paper/2010.08193/

## Key facts

- Cited by 23 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 16 Oct 2020.

## Built on by (most cited first, 23 of 23)

- [Multi-robot Cooperative Pursuit via Potential Field-Enhanced Reinforcement Learning](https://mlsanity.com/paper/2203.04700/) (2022)
- [Learning Multi-Pursuit Evasion for Safe Targeted Navigation of Drones](https://mlsanity.com/paper/2304.03443/) (2023)
- [ESP: Exploiting Symmetry Prior for Multi-Agent Reinforcement Learning](https://mlsanity.com/paper/2307.16186/) (2023)
- [Diffusion-Reinforcement Learning Hierarchical Motion Planning in Multi-agent Adversarial Games](https://mlsanity.com/paper/2403.10794/) (2024)
- [ T3 OMVP: A Transformer-based Time and Team Reinforcement Learning Scheme for Observation-constrained Multi-Vehicle Pursuit in Urban Area](https://mlsanity.com/paper/2203.00183/) (2022)
- [Online Planning for Multi-UAV Pursuit-Evasion in Unknown Environments Using Deep Reinforcement Learning](https://mlsanity.com/paper/2409.15866/) (2024)
- [Learned Controllers for Agile Quadrotors in Pursuit-Evasion Games](https://mlsanity.com/paper/2506.02849/) (2025)
- [Toward multi-target self-organizing pursuit in a partially observable Markov game](https://mlsanity.com/paper/2206.12330/) (2022)
- [Hierarchical Reinforcement Learning for Swarm Confrontation with High Uncertainty](https://mlsanity.com/paper/2406.07877/) (2024)
- [A Dual Curriculum Learning Framework for Multi-UAV Pursuit-Evasion in Diverse Environments](https://mlsanity.com/paper/2312.12255/) (2023)
- [HOLA-Drone: Hypergraphic Open-ended Learning for Zero-Shot Multi-Drone Cooperative Pursuit](https://mlsanity.com/paper/2409.08767/) (2024)
- [TERL: Large-Scale Multi-Target Encirclement Using Transformer-Enhanced Reinforcement Learning](https://mlsanity.com/paper/2503.12395/) (2025)
- [Curriculum Imitation Learning of Distributed Multi-Robot Policies](https://mlsanity.com/paper/2509.25097/) (2025)
- [Mixing Human Demonstrations with Self-Exploration in Experience Replay for Deep Reinforcement Learning](https://mlsanity.com/paper/2107.06840/) (2021)
- [Progression Cognition Reinforcement Learning with Prioritized Experience for Multi-Vehicle Pursuit](https://mlsanity.com/paper/2306.05016/) (2023)
- [Replication of Multi-agent Reinforcement Learning for the "Hide and Seek" Problem](https://mlsanity.com/paper/2310.05430/) (2023)
- [Multi-Robot Pursuit in Parameterized Formation via Imitation Learning](https://mlsanity.com/paper/2410.23586/) (2024)
- [TRUST-UP: Trustworthy Reinforcement learning Using Safe Techniques for UAV Pursuit](https://mlsanity.com/paper/2411.17552/) (2024)
- [AT-Drone: Benchmarking Adaptive Teaming in Multi-Drone Pursuit](https://mlsanity.com/paper/2502.09762/) (2025)
- [ARBoids: Adaptive Residual Reinforcement Learning With Boids Model for Cooperative Multi-USV Target Defense](https://mlsanity.com/paper/2502.18549/) (2025)
- [Strategic Communication under Threat: Learning Information Trade-offs in Pursuit-Evasion Games](https://mlsanity.com/paper/2510.07813/) (2025)
- [Decentralized End-to-End Multi-AAV Pursuit Using Predictive Spatio-Temporal Observation via Deep Reinforcement Learning](https://mlsanity.com/paper/2603.24238/) (2026)
- [M2GRPO: Mamba-based Multi-Agent Group Relative Policy Optimization for Biomimetic Underwater Robots Pursuit](https://mlsanity.com/paper/2604.19404/) (2026)

## Abstract (arXiv)

Pursuit-evasion is the problem of capturing mobile targets with one or more pursuers. We use deep reinforcement learning for pursuing an omni-directional target with multiple, homogeneous agents that are subject to unicycle kinematic constraints. We use shared experience to train a policy for a given number of pursuers that is executed independently by each agent at run-time. The training benefits from curriculum learning, a sweeping-angle ordering to locally represent neighboring agents and encouraging good formations with reward structure that combines individual and group rewards. Simulated experiments with a reactive evader and up to eight pursuers show that our learning-based approach, with non-holonomic agents, performs on par with classical algorithms with omni-directional agents, and outperforms their non-holonomic adaptations. The learned policy is successfully transferred to the real world in a proof-of-concept demonstration with three motion-constrained pursuer drones.