{"ID":2874493,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2509.04535","arxiv_id":"2509.04535","title":"In-Context Policy Adaptation via Cross-Domain Skill Diffusion","abstract":"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 cross-domain settings. The framework enables rapid adaptation of skill-based reinforcement learning policies to diverse target domains, especially under stringent constraints on no model updates and only limited target domain data. Specifically, the framework employs a cross-domain skill diffusion scheme, where domain-agnostic prototype skills and a domain-grounded skill adapter are learned jointly and effectively from an offline dataset through cross-domain consistent diffusion processes. The prototype skills act as primitives for common behavior representations of long-horizon policies, serving as a lingua franca to bridge different domains. Furthermore, to enhance the in-context adaptation performance, we develop a dynamic domain prompting scheme that guides the diffusion-based skill adapter toward better alignment with the target domain. Through experiments with robotic manipulation in Metaworld and autonomous driving in CARLA, we show that our $\\oursol$ framework achieves superior policy adaptation performance under limited target domain data conditions for various cross-domain configurations including differences in environment dynamics, agent embodiment, and task horizon.","short_abstract":"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 cross-domain settings. The framework enables rapid adaptation of skill-based reinforcement learning policies to diverse target domains, esp...","url_abs":"https://arxiv.org/abs/2509.04535","url_pdf":"https://arxiv.org/pdf/2509.04535v1","authors":"[\"Minjong Yoo\",\"Woo Kyung Kim\",\"Honguk Woo\"]","published":"2025-09-04T06:55:38Z","proceeding":"cs.RO","tasks":"[\"cs.RO\",\"cs.AI\",\"cs.LG\"]","methods":"[\"Reinforcement Learning\",\"Diffusion Model\"]","has_code":false}