Decoupled Hierarchical Reinforcement Learning with State Abstraction for Discrete Grids

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Xiao, Qingyu, Chang, Yuanlin, Du, Youtian
Formato: Preprint
Publicado: 2025
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866913871935045632
author Xiao, Qingyu
Chang, Yuanlin
Du, Youtian
author_facet Xiao, Qingyu
Chang, Yuanlin
Du, Youtian
contents Effective agent exploration remains a core challenge in reinforcement learning (RL) for complex discrete state-space environments, particularly under partial observability. This paper presents a decoupled hierarchical RL framework integrating state abstraction (DcHRL-SA) to address this issue. The proposed method employs a dual-level architecture, consisting of a high level RL-based actor and a low-level rule-based policy, to promote effective exploration. Additionally, state abstraction method is incorporated to cluster discrete states, effectively lowering state dimensionality. Experiments conducted in two discrete customized grid environments demonstrate that the proposed approach consistently outperforms PPO in terms of exploration efficiency, convergence speed, cumulative reward, and policy stability. These results demonstrate a practical approach for integrating decoupled hierarchical policies and state abstraction in discrete grids with large-scale exploration space. Code will be available at https://github.com/XQY169/DcHRL-SA.
format Preprint
id arxiv_https___arxiv_org_abs_2506_02050
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Decoupled Hierarchical Reinforcement Learning with State Abstraction for Discrete Grids
Xiao, Qingyu
Chang, Yuanlin
Du, Youtian
Machine Learning
Artificial Intelligence
Effective agent exploration remains a core challenge in reinforcement learning (RL) for complex discrete state-space environments, particularly under partial observability. This paper presents a decoupled hierarchical RL framework integrating state abstraction (DcHRL-SA) to address this issue. The proposed method employs a dual-level architecture, consisting of a high level RL-based actor and a low-level rule-based policy, to promote effective exploration. Additionally, state abstraction method is incorporated to cluster discrete states, effectively lowering state dimensionality. Experiments conducted in two discrete customized grid environments demonstrate that the proposed approach consistently outperforms PPO in terms of exploration efficiency, convergence speed, cumulative reward, and policy stability. These results demonstrate a practical approach for integrating decoupled hierarchical policies and state abstraction in discrete grids with large-scale exploration space. Code will be available at https://github.com/XQY169/DcHRL-SA.
title Decoupled Hierarchical Reinforcement Learning with State Abstraction for Discrete Grids
topic Machine Learning
Artificial Intelligence
url https://arxiv.org/abs/2506.02050