arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2203.00352cs.ROcs.AIcs.CVcs.LG
收藏

从实践中学习可供性,实现样本高效的策略学习

Affordance Learning from Play for Sample-Efficient Policy Learning

University of Freiburg(弗莱堡大学)

Jessica Borja-Diaz, Oier Mees, Gabriel Kalweit, Lukas Hermann, Joschka Boedecker, Wolfram Burgard

摘要:

在以人为中心的环境中运行的机器人应该有能力理解物体的功能:每个物体可以做什么,这种交互可能发生在哪里,以及如何使用物体来实现目标。为此,我们提出了一种新的方法,从人类遥控游戏数据中提取一个自我监督的视觉启示模型,并利用它来实现有效的策略学习和运动规划。我们将基于模型的规划与无模型的深度强化学习(RL)相结合,以学习有利于人们喜欢的相同对象区域的策略,同时需要最少的机器人与环境的交互。我们评估我们的算法,视觉负担指导的政策优化(VAPO),与不同的模拟操作任务和现实世界的机器人整理实验,以证明我们的负担指导政策的有效性。我们发现,我们的政策训练比基线快4倍,更好地推广到新的对象,因为我们的视觉启示模型可以预测他们的启示区域。

英文摘要:

Robots operating in human-centered environments should have the ability to understand how objects function: what can be done with each object, where this interaction may occur, and how the object is used to achieve a goal. To this end, we propose a novel approach that extracts a self-supervised visual affordance model from human teleoperated play data and leverages it to enable efficient policy learning and motion planning. We combine model-based planning with model-free deep reinforcement learning (RL) to learn policies that favor the same object regions favored by people, while requiring minimal robot interactions with the environment. We evaluate our algorithm, Visual Affordance-guided Policy Optimization (VAPO), with both diverse simulation manipulation tasks and real world robot tidy-up experiments to demonstrate the effectiveness of our affordance-guided policies. We find that our policies train 4x faster than the baselines and generalize better to novel objects because our visual affordance model can anticipate their affordance regions.

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。

↑