arXivDaily arXiv每日学术速递 周一至周五更新
北美退伍军人节(Veterans Day),12 日无更新
arXiv 2104.08795cs.LGcs.ROcs.SYeess.SY
收藏

直观的物理引导探索样品高效的Sim2real转移

Intuitive Physics Guided Exploration for Sample Efficient Sim2real Transfer

Deakin University(迪肯大学);Applied Artificial Intelligence Institute(应用人工智能研究所)

Buddhika Laknath Semage, Thommen George Karimpanal, Santu Rana, Svetha Venkatesh

摘要:

基于物理的强化学习任务可以从简化的物理模拟器中受益,因为它们可能允许在模拟中学习接近最优的策略。然而,这种模拟器需要潜在的因素(例如,质量,摩擦系数等)。相关物体和其他环境特定因素(如风速、空气密度等)的影响。准确地指定,否则,可能需要相当多的额外学习努力来使学习的仿真策略适应真实环境。由于这样一个完整的规范可能是不切实际的,在本文中,我们相反,专注于学习特定于任务的潜在因素的估计,允许在理想的仿真环境中的真实世界的轨迹近似。具体来说,我们提出了两个新的概念:a)动作分组的想法,某些类型的行动与某些潜在因素的估计密切相关,和; b)部分接地的想法,模拟特定于任务的动态可能不需要精确估计的所有潜在因素。我们首先介绍基于人类物理知识和经验的直观动作分组,然后用于设计与真实环境交互的新颖策略。接下来,我们描述了如何在给定的环境中的任务的先验知识可以用来提取不同的潜在因素的相对重要性,以及如何可以用来通知部分接地,这使得在任何任意环境中的任务的有效学习。我们在一系列基于物理的任务中展示了我们的方法,并表明它相对于其他基线实现了卓越的性能,仅使用有限数量的真实世界的交互。

英文摘要:

Physics-based reinforcement learning tasks can benefit from simplified physics simulators as they potentially allow near-optimal policies to be learned in simulation. However, such simulators require the latent factors (e.g. mass, friction coefficient etc.) of the associated objects and other environment-specific factors (e.g. wind speed, air density etc.) to be accurately specified, without which, it could take considerable additional learning effort to adapt the learned simulation policy to the real environment. As such a complete specification can be impractical, in this paper, we instead, focus on learning task-specific estimates of latent factors which allow the approximation of real world trajectories in an ideal simulation environment. Specifically, we propose two new concepts: a) action grouping - the idea that certain types of actions are closely associated with the estimation of certain latent factors, and; b) partial grounding - the idea that simulation of task-specific dynamics may not need precise estimation of all the latent factors. We first introduce intuitive action groupings based on human physics knowledge and experience, which is then used to design novel strategies for interacting with the real environment. Next, we describe how prior knowledge of a task in a given environment can be used to extract the relative importance of different latent factors, and how this can be used to inform partial grounding, which enables efficient learning of the task in any arbitrary environment. We demonstrate our approach in a range of physics based tasks, and show that it achieves superior performance relative to other baselines, using only a limited number of real-world interactions.

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。

↑