NaviMaster: Learning a Unified Policy for GUI and Embodied Navigation Tasks

TL;DR

NaviMaster introduces a unified reinforcement learning framework that combines GUI and embodied navigation tasks, leveraging a shared data collection and reward strategy to improve generalization and performance across benchmarks.

Contribution

It is the first to unify GUI and embodied navigation tasks within a single framework using a common MDP formulation and training pipeline.

Findings

Outperforms state-of-the-art in GUI navigation and embodied tasks.

Effective data mixing and reward design improve learning efficiency.

Unified training strategy enhances generalization across benchmarks.

Abstract

Recent advances in Graphical User Interface (GUI) and embodied navigation have driven progress, yet these domains have largely evolved in isolation, with disparate datasets and training paradigms. In this paper, we observe that both tasks can be formulated as Markov Decision Processes (MDP), suggesting a foundational principle for their unification. Hence, we present NaviMaster, the first unified agent capable of unifying GUI navigation and embodied navigation within a single framework. Specifically, NaviMaster (i) proposes a visual-target trajectory collection pipeline that generates trajectories for both GUI and embodied tasks using a single formulation. (ii) employs a unified reinforcement learning framework on the mix data to improve generalization. (iii) designs a novel distance-aware reward to ensure efficient learning from the trajectories. Through extensive experiments on out-of-domain benchmarks, NaviMaster is shown to outperform state-of-the-art agents in GUI navigation, spatial affordance prediction, and embodied navigation. Ablation studies further demonstrate the efficacy of our unified training strategy, data mixing strategy, and reward design. Our codes, data, and checkpoints are available at https://iron-boyy.github.io/navimaster-page/.