Decoupled Hierarchical Reinforcement Learning with State Abstraction for Discrete Grids

TL;DR

This paper introduces a decoupled hierarchical reinforcement learning framework with state abstraction for discrete grid environments, significantly improving exploration efficiency and convergence speed in complex, partially observable settings.

Contribution

It proposes a novel dual-level RL architecture combined with state abstraction, enhancing exploration and learning in large discrete state spaces.

Findings

Outperforms PPO in exploration efficiency

Achieves faster convergence and higher rewards

Demonstrates policy stability in complex environments

Abstract

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.