Decision MetaMamba: Enhancing Selective SSM in Offline RL with Heterogeneous Sequence Mixing

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Kim, Wall, Song, Chaeyoung, Kim, Hanul
Formato: Preprint
Publicado: 2026
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866912927421825024
author Kim, Wall
Song, Chaeyoung
Kim, Hanul
author_facet Kim, Wall
Song, Chaeyoung
Kim, Hanul
contents Mamba-based models have drawn much attention in offline RL. However, their selective mechanism often detrimental when key steps in RL sequences are omitted. To address these issues, we propose a simple yet effective structure, called Decision MetaMamba (DMM), which replaces Mamba's token mixer with a dense layer-based sequence mixer and modifies positional structure to preserve local information. By performing sequence mixing that considers all channels simultaneously before Mamba, DMM prevents information loss due to selective scanning and residual gating. Extensive experiments demonstrate that our DMM delivers the state-of-the-art performance across diverse RL tasks. Furthermore, DMM achieves these results with a compact parameter footprint, demonstrating strong potential for real-world applications.
format Preprint
id arxiv_https___arxiv_org_abs_2602_19805
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Decision MetaMamba: Enhancing Selective SSM in Offline RL with Heterogeneous Sequence Mixing
Kim, Wall
Song, Chaeyoung
Kim, Hanul
Machine Learning
Artificial Intelligence
Mamba-based models have drawn much attention in offline RL. However, their selective mechanism often detrimental when key steps in RL sequences are omitted. To address these issues, we propose a simple yet effective structure, called Decision MetaMamba (DMM), which replaces Mamba's token mixer with a dense layer-based sequence mixer and modifies positional structure to preserve local information. By performing sequence mixing that considers all channels simultaneously before Mamba, DMM prevents information loss due to selective scanning and residual gating. Extensive experiments demonstrate that our DMM delivers the state-of-the-art performance across diverse RL tasks. Furthermore, DMM achieves these results with a compact parameter footprint, demonstrating strong potential for real-world applications.
title Decision MetaMamba: Enhancing Selective SSM in Offline RL with Heterogeneous Sequence Mixing
topic Machine Learning
Artificial Intelligence
url https://arxiv.org/abs/2602.19805