collaborators

6 papers

cs.RO2025

In-Context Policy Adaptation via Cross-Domain Skill Diffusion

Minjong Yoo, Woo Kyung Kim, Honguk Woo

In this work, we present an in-context policy adaptation (ICPAD) framework designed for long-horizon multi-task environments, exploring diffusion-based skill learning techniques in…

cs.LG2025

Incremental Learning of Retrievable Skills For Efficient Continual Task Adaptation

Daehee Lee, Minjong Yoo, Woo Kyung Kim +2

Continual Imitation Learning (CiL) involves extracting and accumulating task knowledge from demonstrations across multiple stages and tasks to achieve a multi-task policy. With rec…

cs.AI2024

Embodied CoT Distillation From LLM To Off-the-shelf Agents

Wonje Choi, Woo Kyung Kim, Minjong Yoo +1

We address the challenge of utilizing large language models (LLMs) for complex embodied tasks, in the environment where decision-making systems operate timely on capacity-limited,…

cs.AI2024

Efficient Policy Adaptation with Contrastive Prompt Ensemble for Embodied Agents

Wonje Choi, Woo Kyung Kim, SeungHyun Kim +1

For embodied reinforcement learning (RL) agents interacting with the environment, it is desirable to have rapid policy adaptation to unseen visual observations, but achieving zero-…

cs.LG2024

Pareto Inverse Reinforcement Learning for Diverse Expert Policy Generation

Woo Kyung Kim, Minjong Yoo, Honguk Woo

Data-driven offline reinforcement learning and imitation learning approaches have been gaining popularity in addressing sequential decision-making problems. Yet, these approaches r…

cs.LG2024

Robust Policy Learning via Offline Skill Diffusion

Woo Kyung Kim, Minjong Yoo, Honguk Woo

Skill-based reinforcement learning (RL) approaches have shown considerable promise, especially in solving long-horizon tasks via hierarchical structures. These skills, learned task…