Pursuit-evasion with Decentralized Robotic Swarm in Continuous State Space and Action Space via Deep Reinforcement Learning

Gurpreet Singh, Daniel M. Lofaro, Donald Sofge

2020

Abstract

In this paper we address the pursuit-evasion problem using deep reinforcement learning techniques. The goal of this project is to train each agent in a swarm of pursuers to learn a control strategy to capture the evaders in optimal time while displaying collaborative behavior. Additional challenges addressed in this paper include the use of continuous agent state and action spaces, and the requirement that agents in the swarm must take actions in a decentralized fashion. Our technique builds on the actor-critic model-free Multi-Agent Deep Deterministic Policy Gradient (MADDPG) algorithm that operates over continuous spaces. The evader strategy is not learned and is based on Voronoi regions, which the pursuers try to minimize and the evader tries to maximize. We assume global visibility of all agents at all times. We implement the algorithm and train the models using Python Pytorch machine learning library. Our results show that the pursuers can learn a control strategy to capture evaders.

Download


Paper Citation


in Harvard Style

Singh G., Lofaro D. and Sofge D. (2020). Pursuit-evasion with Decentralized Robotic Swarm in Continuous State Space and Action Space via Deep Reinforcement Learning. In Proceedings of the 12th International Conference on Agents and Artificial Intelligence - Volume 1: ICAART, ISBN 978-989-758-395-7, pages 226-233. DOI: 10.5220/0008971502260233


in Bibtex Style

@conference{icaart20,
author={Gurpreet Singh and Daniel Lofaro and Donald Sofge},
title={Pursuit-evasion with Decentralized Robotic Swarm in Continuous State Space and Action Space via Deep Reinforcement Learning},
booktitle={Proceedings of the 12th International Conference on Agents and Artificial Intelligence - Volume 1: ICAART,},
year={2020},
pages={226-233},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0008971502260233},
isbn={978-989-758-395-7},
}


in EndNote Style

TY - CONF

JO - Proceedings of the 12th International Conference on Agents and Artificial Intelligence - Volume 1: ICAART,
TI - Pursuit-evasion with Decentralized Robotic Swarm in Continuous State Space and Action Space via Deep Reinforcement Learning
SN - 978-989-758-395-7
AU - Singh G.
AU - Lofaro D.
AU - Sofge D.
PY - 2020
SP - 226
EP - 233
DO - 10.5220/0008971502260233