no code implementations • 1 Mar 2024 • Woo Kyung Kim, Minjong Yoo, Honguk Woo
These skills, learned task-agnostically from offline datasets, can accelerate the policy learning process for new tasks.
no code implementations • 13 Feb 2024 • Sangwoo Shin, Daehee Lee, Minjong Yoo, Woo Kyung Kim, Honguk Woo
One-shot imitation is to learn a new task from a single demonstration, yet it is a challenging problem to adopt it for complex tasks with the high domain diversity inherent in a non-stationary environment.
no code implementations • 12 Feb 2024 • Sangwoo Shin, Minjong Yoo, Jeongwoo Lee, Honguk Woo
In these cross-domain settings, we present a semantic skill translator framework SemTra which utilizes a set of multi-modal models to extract skills from the snippets, and leverages the reasoning capabilities of a pretrained language model to adapt these extracted skills to the target domain.