Safe Continuous-time Multi-Agent Reinforcement Learning via Epigraph Form

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Wang, Xuefeng, Zhang, Lei, Pu, Henglin, Li, Husheng, Qureshi, Ahmed H.
Formato: Preprint
Publicado: 2026
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866908840587427840
author Wang, Xuefeng
Zhang, Lei
Pu, Henglin
Li, Husheng
Qureshi, Ahmed H.
author_facet Wang, Xuefeng
Zhang, Lei
Pu, Henglin
Li, Husheng
Qureshi, Ahmed H.
contents Multi-agent reinforcement learning (MARL) has made significant progress in recent years, but most algorithms still rely on a discrete-time Markov Decision Process (MDP) with fixed decision intervals. This formulation is often ill-suited for complex multi-agent dynamics, particularly in high-frequency or irregular time-interval settings, leading to degraded performance and motivating the development of continuous-time MARL (CT-MARL). Existing CT-MARL methods are mainly built on Hamilton-Jacobi-Bellman (HJB) equations. However, they rarely account for safety constraints such as collision penalties, since these introduce discontinuities that make HJB-based learning difficult. To address this challenge, we propose a continuous-time constrained MDP (CT-CMDP) formulation and a novel MARL framework that transforms discrete MDPs into CT-CMDPs via an epigraph-based reformulation. We then solve this by proposing a novel physics-informed neural network (PINN)-based actor-critic method that enables stable and efficient optimization in continuous time. We evaluate our approach on continuous-time safe multi-particle environments (MPE) and safe multi-agent MuJoCo benchmarks. Results demonstrate smoother value approximations, more stable training, and improved performance over safe MARL baselines, validating the effectiveness and robustness of our method.
format Preprint
id arxiv_https___arxiv_org_abs_2602_17078
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Safe Continuous-time Multi-Agent Reinforcement Learning via Epigraph Form
Wang, Xuefeng
Zhang, Lei
Pu, Henglin
Li, Husheng
Qureshi, Ahmed H.
Multiagent Systems
Multi-agent reinforcement learning (MARL) has made significant progress in recent years, but most algorithms still rely on a discrete-time Markov Decision Process (MDP) with fixed decision intervals. This formulation is often ill-suited for complex multi-agent dynamics, particularly in high-frequency or irregular time-interval settings, leading to degraded performance and motivating the development of continuous-time MARL (CT-MARL). Existing CT-MARL methods are mainly built on Hamilton-Jacobi-Bellman (HJB) equations. However, they rarely account for safety constraints such as collision penalties, since these introduce discontinuities that make HJB-based learning difficult. To address this challenge, we propose a continuous-time constrained MDP (CT-CMDP) formulation and a novel MARL framework that transforms discrete MDPs into CT-CMDPs via an epigraph-based reformulation. We then solve this by proposing a novel physics-informed neural network (PINN)-based actor-critic method that enables stable and efficient optimization in continuous time. We evaluate our approach on continuous-time safe multi-particle environments (MPE) and safe multi-agent MuJoCo benchmarks. Results demonstrate smoother value approximations, more stable training, and improved performance over safe MARL baselines, validating the effectiveness and robustness of our method.
title Safe Continuous-time Multi-Agent Reinforcement Learning via Epigraph Form
topic Multiagent Systems
url https://arxiv.org/abs/2602.17078