arXiv 2506.126762025-06-15cs.RO

面向多目标机器人操作任务的基于目标的自适应生成对抗模仿学习（Goal-SAGAIL）

Goal-based Self-Adaptive Generative Adversarial Imitation Learning (Goal-SAGAIL) for Multi-goal Robotic Manipulation Tasks

College of Engineering and Physical Sciences, Aston University（工程与物理科学学院，阿斯顿大学）；Department of Computer Science Department, Loughborough University（计算机科学系，洛桑大学）

Yingyi Kuang, Luis J. Manso, George Vogiatzis

备注：: 6 pages, 5 figures

阅读 PDF

arXiv 页面 ↗HTML 原文 ↗

AI总结：

针对多目标机器人操作任务中演示数据覆盖不足导致学习偏向简单子任务的问题，提出结合自适应学习与目标条件GAIL的Goal-SAGAIL框架，在有限非最优演示下显著提升多场景学习效率。

摘要：

针对多目标机器人操作任务的强化学习因目标空间的多样性与复杂性面临显著挑战。后见经验回放（Hindsight Experience Replay，HER）等技术已被提出以提升此类任务的学习效率。近期，研究人员将HER与生成对抗模仿学习（Generative Adversarial Imitation Learning，GAIL）等先进模仿学习方法相结合，以整合演示数据并加快训练速度。然而，演示数据往往无法充分覆盖目标空间，尤其是从人类遥操作中获取的数据时更是如此。这会导致从演示中学习的过程偏向于掌握较简单的子任务，而非处理更具挑战性的子任务。在本研究中，我们提出了基于目标的自适应生成对抗模仿学习（Goal-SAGAIL），这是一款专门为多目标机器人操作任务设计的新型框架。通过将自适应学习原理与以目标为条件的GAIL相结合，我们的方法即使在演示数据有限且非最优的情况下，也能提升模仿学习的效率。实验结果证实，在仿真和人类专家提供的非最优演示条件下，我们的方法在多种多目标操作场景（包括复杂的手部操作任务）中均显著提升了学习效率。

英文摘要：

Reinforcement learning for multi-goal robot manipulation tasks poses significant challenges due to the diversity and complexity of the goal space. Techniques such as Hindsight Experience Replay (HER) have been introduced to improve learning efficiency for such tasks. More recently, researchers have combined HER with advanced imitation learning methods such as Generative Adversarial Imitation Learning (GAIL) to integrate demonstration data and accelerate training speed. However, demonstration data often fails to provide enough coverage for the goal space, especially when acquired from human teleoperation. This biases the learning-from-demonstration process toward mastering easier sub-tasks instead of tackling the more challenging ones. In this work, we present Goal-based Self-Adaptive Generative Adversarial Imitation Learning (Goal-SAGAIL), a novel framework specifically designed for multi-goal robot manipulation tasks. By integrating self-adaptive learning principles with goal-conditioned GAIL, our approach enhances imitation learning efficiency, even when limited, suboptimal demonstrations are available. Experimental results validate that our method significantly improves learning efficiency across various multi-goal manipulation scenarios -- including complex in-hand manipulation tasks -- using suboptimal demonstrations provided by both simulation and human experts.

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。