Multi-Agent Reinforcement Learning with a Hierarchy of Reward Machines

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Zheng, Xuejing, Yu, Chao
Formato: Preprint
Publicado: 2024
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866929273292455936
author Zheng, Xuejing
Yu, Chao
author_facet Zheng, Xuejing
Yu, Chao
contents In this paper, we study the cooperative Multi-Agent Reinforcement Learning (MARL) problems using Reward Machines (RMs) to specify the reward functions such that the prior knowledge of high-level events in a task can be leveraged to facilitate the learning efficiency. Unlike the existing work that RMs have been incorporated into MARL for task decomposition and policy learning in relatively simple domains or with an assumption of independencies among the agents, we present Multi-Agent Reinforcement Learning with a Hierarchy of RMs (MAHRM) that is capable of dealing with more complex scenarios when the events among agents can occur concurrently and the agents are highly interdependent. MAHRM exploits the relationship of high-level events to decompose a task into a hierarchy of simpler subtasks that are assigned to a small group of agents, so as to reduce the overall computational complexity. Experimental results in three cooperative MARL domains show that MAHRM outperforms other MARL methods using the same prior knowledge of high-level events.
format Preprint
id arxiv_https___arxiv_org_abs_2403_07005
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Multi-Agent Reinforcement Learning with a Hierarchy of Reward Machines
Zheng, Xuejing
Yu, Chao
Artificial Intelligence
Machine Learning
Multiagent Systems
In this paper, we study the cooperative Multi-Agent Reinforcement Learning (MARL) problems using Reward Machines (RMs) to specify the reward functions such that the prior knowledge of high-level events in a task can be leveraged to facilitate the learning efficiency. Unlike the existing work that RMs have been incorporated into MARL for task decomposition and policy learning in relatively simple domains or with an assumption of independencies among the agents, we present Multi-Agent Reinforcement Learning with a Hierarchy of RMs (MAHRM) that is capable of dealing with more complex scenarios when the events among agents can occur concurrently and the agents are highly interdependent. MAHRM exploits the relationship of high-level events to decompose a task into a hierarchy of simpler subtasks that are assigned to a small group of agents, so as to reduce the overall computational complexity. Experimental results in three cooperative MARL domains show that MAHRM outperforms other MARL methods using the same prior knowledge of high-level events.
title Multi-Agent Reinforcement Learning with a Hierarchy of Reward Machines
topic Artificial Intelligence
Machine Learning
Multiagent Systems
url https://arxiv.org/abs/2403.07005