LaMOuR: Leveraging Language Models for Out-of-Distribution Recovery in Reinforcement Learning

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Kim, Chan, Seo, Seung-Woo, Kim, Seong-Woo
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866916664441831424
author Kim, Chan
Seo, Seung-Woo
Kim, Seong-Woo
author_facet Kim, Chan
Seo, Seung-Woo
Kim, Seong-Woo
contents Deep Reinforcement Learning (DRL) has demonstrated strong performance in robotic control but remains susceptible to out-of-distribution (OOD) states, often resulting in unreliable actions and task failure. While previous methods have focused on minimizing or preventing OOD occurrences, they largely neglect recovery once an agent encounters such states. Although the latest research has attempted to address this by guiding agents back to in-distribution states, their reliance on uncertainty estimation hinders scalability in complex environments. To overcome this limitation, we introduce Language Models for Out-of-Distribution Recovery (LaMOuR), which enables recovery learning without relying on uncertainty estimation. LaMOuR generates dense reward codes that guide the agent back to a state where it can successfully perform its original task, leveraging the capabilities of LVLMs in image description, logical reasoning, and code generation. Experimental results show that LaMOuR substantially enhances recovery efficiency across diverse locomotion tasks and even generalizes effectively to complex environments, including humanoid locomotion and mobile manipulation, where existing methods struggle. The code and supplementary materials are available at https://lamour-rl.github.io/.
format Preprint
id arxiv_https___arxiv_org_abs_2503_17125
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle LaMOuR: Leveraging Language Models for Out-of-Distribution Recovery in Reinforcement Learning
Kim, Chan
Seo, Seung-Woo
Kim, Seong-Woo
Robotics
Artificial Intelligence
Deep Reinforcement Learning (DRL) has demonstrated strong performance in robotic control but remains susceptible to out-of-distribution (OOD) states, often resulting in unreliable actions and task failure. While previous methods have focused on minimizing or preventing OOD occurrences, they largely neglect recovery once an agent encounters such states. Although the latest research has attempted to address this by guiding agents back to in-distribution states, their reliance on uncertainty estimation hinders scalability in complex environments. To overcome this limitation, we introduce Language Models for Out-of-Distribution Recovery (LaMOuR), which enables recovery learning without relying on uncertainty estimation. LaMOuR generates dense reward codes that guide the agent back to a state where it can successfully perform its original task, leveraging the capabilities of LVLMs in image description, logical reasoning, and code generation. Experimental results show that LaMOuR substantially enhances recovery efficiency across diverse locomotion tasks and even generalizes effectively to complex environments, including humanoid locomotion and mobile manipulation, where existing methods struggle. The code and supplementary materials are available at https://lamour-rl.github.io/.
title LaMOuR: Leveraging Language Models for Out-of-Distribution Recovery in Reinforcement Learning
topic Robotics
Artificial Intelligence
url https://arxiv.org/abs/2503.17125