vix.ing · top · new · best · stats · spec

MaIL: Improving Imitation Learning with Mamba

2024/06/12 by Xiaogang Jia, Qian Wang, Jia, Xiaogang +17 · 4 citations
Engineering · Neuroscience · Social Sciences · #Educational Tools and Methods #FOS: Computer and information sciences #Human Motion and Animation #Machine Learning (cs.LG) #Robotics (cs.RO) #Tactile and Sensory Interactions

paper · pdf · doi:10.48550/arxiv.2406.08234

openalex publication_date 2024/06/12 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

This work presents Mamba Imitation Learning (MaIL), a novel imitation learning (IL) architecture that provides an alternative to state-of-the-art (SoTA) Transformer-based policies. MaIL leverages Mamba, a state-space model designed to selectively focus on key features of the data. While Transformers are highly effective in data-rich environments due to their dense attention mechanisms, they can struggle with smaller datasets, often leading to overfitting or suboptimal representation learning. In contrast, Mamba's architecture enhances representation learning efficiency by focusing on key features and reducing model complexity. This approach mitigates overfitting and enhances generalization, even when working with limited data. Extensive evaluations on the LIBERO benchmark demonstrate that MaIL consistently outperforms Transformers on all LIBERO tasks with limited data and matches their performance when the full dataset is available. Additionally, MaIL's effectiveness is validated through its superior performance in three real robot experiments. Our code is available at https://github.com/ALRhub/MaIL.

Cited by

Related