Learning with Expert Abstractions for Efficient Multi-Task Continuous Control

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Jewett, Jeff, Saisubramanian, Sandhya
Formato: Preprint
Publicado: 2025
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866917961080504320
author Jewett, Jeff
Saisubramanian, Sandhya
author_facet Jewett, Jeff
Saisubramanian, Sandhya
contents Decision-making in complex, continuous multi-task environments is often hindered by the difficulty of obtaining accurate models for planning and the inefficiency of learning purely from trial and error. While precise environment dynamics may be hard to specify, human experts can often provide high-fidelity abstractions that capture the essential high-level structure of a task and user preferences in the target environment. Existing hierarchical approaches often target discrete settings and do not generalize across tasks. We propose a hierarchical reinforcement learning approach that addresses these limitations by dynamically planning over the expert-specified abstraction to generate subgoals to learn a goal-conditioned policy. To overcome the challenges of learning under sparse rewards, we shape the reward based on the optimal state value in the abstract model. This structured decision-making process enhances sample efficiency and facilitates zero-shot generalization. Our empirical evaluation on a suite of procedurally generated continuous control environments demonstrates that our approach outperforms existing hierarchical reinforcement learning methods in terms of sample efficiency, task completion rate, scalability to complex tasks, and generalization to novel scenarios.
format Preprint
id arxiv_https___arxiv_org_abs_2503_14809
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Learning with Expert Abstractions for Efficient Multi-Task Continuous Control
Jewett, Jeff
Saisubramanian, Sandhya
Machine Learning
Artificial Intelligence
Decision-making in complex, continuous multi-task environments is often hindered by the difficulty of obtaining accurate models for planning and the inefficiency of learning purely from trial and error. While precise environment dynamics may be hard to specify, human experts can often provide high-fidelity abstractions that capture the essential high-level structure of a task and user preferences in the target environment. Existing hierarchical approaches often target discrete settings and do not generalize across tasks. We propose a hierarchical reinforcement learning approach that addresses these limitations by dynamically planning over the expert-specified abstraction to generate subgoals to learn a goal-conditioned policy. To overcome the challenges of learning under sparse rewards, we shape the reward based on the optimal state value in the abstract model. This structured decision-making process enhances sample efficiency and facilitates zero-shot generalization. Our empirical evaluation on a suite of procedurally generated continuous control environments demonstrates that our approach outperforms existing hierarchical reinforcement learning methods in terms of sample efficiency, task completion rate, scalability to complex tasks, and generalization to novel scenarios.
title Learning with Expert Abstractions for Efficient Multi-Task Continuous Control
topic Machine Learning
Artificial Intelligence
url https://arxiv.org/abs/2503.14809