2 papers
cs.AI2025
Exploratory Retrieval-Augmented Planning For Continual Embodied Instruction Following
Minjong Yoo, Jinwoo Jang, Wei-jin Park +1
This study presents an Exploratory Retrieval-Augmented Planning (ExRAP) framework, designed to tackle continual instruction following tasks of embodied agents in dynamic, non-stati…
cs.AI2024
LLM-Based Offline Learning for Embodied Agents via Consistency-Guided Reward Ensemble
Yujeong Lee, Sangwoo Shin, Wei-Jin Park +1
Employing large language models (LLMs) to enable embodied agents has become popular, yet it presents several limitations in practice. In this work, rather than using LLMs directly…