SELU: Self-Learning Embodied MLLMs in Unknown Environments

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Li, Boyu, Jiang, Haobin, Ding, Ziluo, Xu, Xinrun, Li, Haoran, Zhao, Dongbin, Lu, Zongqing
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916423309197312
author Li, Boyu
Jiang, Haobin
Ding, Ziluo
Xu, Xinrun
Li, Haoran
Zhao, Dongbin
Lu, Zongqing
author_facet Li, Boyu
Jiang, Haobin
Ding, Ziluo
Xu, Xinrun
Li, Haoran
Zhao, Dongbin
Lu, Zongqing
contents Recently, multimodal large language models (MLLMs) have demonstrated strong visual understanding and decision-making capabilities, enabling the exploration of autonomously improving MLLMs in unknown environments. However, external feedback like human or environmental feedback is not always available. To address this challenge, existing methods primarily focus on enhancing the decision-making capabilities of MLLMs through voting and scoring mechanisms, while little effort has been paid to improving the environmental comprehension of MLLMs in unknown environments. To fully unleash the self-learning potential of MLLMs, we propose a novel actor-critic self-learning paradigm, dubbed SELU, inspired by the actor-critic paradigm in reinforcement learning. The critic employs self-asking and hindsight relabeling to extract knowledge from interaction trajectories collected by the actor, thereby augmenting its environmental comprehension. Simultaneously, the actor is improved by the self-feedback provided by the critic, enhancing its decision-making. We evaluate our method in the AI2-THOR and VirtualHome environments, and SELU achieves critic improvements of approximately 28% and 30%, and actor improvements of about 20% and 24% via self-learning.
format Preprint
id arxiv_https___arxiv_org_abs_2410_03303
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle SELU: Self-Learning Embodied MLLMs in Unknown Environments
Li, Boyu
Jiang, Haobin
Ding, Ziluo
Xu, Xinrun
Li, Haoran
Zhao, Dongbin
Lu, Zongqing
Machine Learning
Computer Vision and Pattern Recognition
Recently, multimodal large language models (MLLMs) have demonstrated strong visual understanding and decision-making capabilities, enabling the exploration of autonomously improving MLLMs in unknown environments. However, external feedback like human or environmental feedback is not always available. To address this challenge, existing methods primarily focus on enhancing the decision-making capabilities of MLLMs through voting and scoring mechanisms, while little effort has been paid to improving the environmental comprehension of MLLMs in unknown environments. To fully unleash the self-learning potential of MLLMs, we propose a novel actor-critic self-learning paradigm, dubbed SELU, inspired by the actor-critic paradigm in reinforcement learning. The critic employs self-asking and hindsight relabeling to extract knowledge from interaction trajectories collected by the actor, thereby augmenting its environmental comprehension. Simultaneously, the actor is improved by the self-feedback provided by the critic, enhancing its decision-making. We evaluate our method in the AI2-THOR and VirtualHome environments, and SELU achieves critic improvements of approximately 28% and 30%, and actor improvements of about 20% and 24% via self-learning.
title SELU: Self-Learning Embodied MLLMs in Unknown Environments
topic Machine Learning
Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2410.03303