Picture for Minjong Yoo

Minjong Yoo

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

Add code
Dec 16, 2024
Viaarxiv icon

Incremental Learning of Retrievable Skills For Efficient Continual Task Adaptation

Add code
Oct 30, 2024
Viaarxiv icon

Skills Regularized Task Decomposition for Multi-task Offline Reinforcement Learning

Add code
Aug 28, 2024
Viaarxiv icon

Pareto Inverse Reinforcement Learning for Diverse Expert Policy Generation

Add code
Aug 22, 2024
Viaarxiv icon

Offline Policy Learning via Skill-step Abstraction for Long-horizon Goal-Conditioned Tasks

Add code
Aug 21, 2024
Viaarxiv icon

Model Adaptation for Time Constrained Embodied Control

Add code
Jun 17, 2024
Viaarxiv icon

Robust Policy Learning via Offline Skill Diffusion

Add code
Mar 05, 2024
Viaarxiv icon

One-shot Imitation in a Non-Stationary Environment via Multi-Modal Skill

Add code
Feb 13, 2024
Viaarxiv icon

SemTra: A Semantic Skill Translator for Cross-Domain Zero-Shot Policy Adaptation

Add code
Feb 12, 2024
Viaarxiv icon