Hierarchical Reinforcement Learning with Low-Level MPC for Multi-Agent Control

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Studt, Max, Schildbach, Georg
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908584846032896
author Studt, Max
Schildbach, Georg
author_facet Studt, Max
Schildbach, Georg
contents Achieving safe and coordinated behavior in dynamic, constraint-rich environments remains a major challenge for learning-based control. Pure end-to-end learning often suffers from poor sample efficiency and limited reliability, while model-based methods depend on predefined references and struggle to generalize. We propose a hierarchical framework that combines tactical decision-making via reinforcement learning (RL) with low-level execution through Model Predictive Control (MPC). For the case of multi-agent systems this means that high-level policies select abstract targets from structured regions of interest (ROIs), while MPC ensures dynamically feasible and safe motion. Tested on a predator-prey benchmark, our approach outperforms end-to-end and shielding-based RL baselines in terms of reward, safety, and consistency, underscoring the benefits of combining structured learning with model-based control.
format Preprint
id arxiv_https___arxiv_org_abs_2509_15799
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Hierarchical Reinforcement Learning with Low-Level MPC for Multi-Agent Control
Studt, Max
Schildbach, Georg
Systems and Control
Artificial Intelligence
Robotics
Optimization and Control
Achieving safe and coordinated behavior in dynamic, constraint-rich environments remains a major challenge for learning-based control. Pure end-to-end learning often suffers from poor sample efficiency and limited reliability, while model-based methods depend on predefined references and struggle to generalize. We propose a hierarchical framework that combines tactical decision-making via reinforcement learning (RL) with low-level execution through Model Predictive Control (MPC). For the case of multi-agent systems this means that high-level policies select abstract targets from structured regions of interest (ROIs), while MPC ensures dynamically feasible and safe motion. Tested on a predator-prey benchmark, our approach outperforms end-to-end and shielding-based RL baselines in terms of reward, safety, and consistency, underscoring the benefits of combining structured learning with model-based control.
title Hierarchical Reinforcement Learning with Low-Level MPC for Multi-Agent Control
topic Systems and Control
Artificial Intelligence
Robotics
Optimization and Control
url https://arxiv.org/abs/2509.15799