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 2010.04296cs.ROcs.LGstat.ML
收藏

CausalWorld:一个面向因果结构和迁移学习的机器人操作基准

CausalWorld: A Robotic Manipulation Benchmark for Causal Structure and Transfer Learning

ETH Zürich(苏黎世联邦理工学院);MPI Tübingen(图宾根马克斯·普朗克研究所);Mila, University of Montreal(蒙特利尔大学Mila)

Ossama Ahmed, Frederik Träuble, Anirudh Goyal, Alexander Neitz, Yoshua Bengio, Bernhard Schölkopf, Manuel Wüthrich, Stefan Bauer

摘要:

尽管最近强化学习(RL)的成功,它仍然是一个挑战,代理人学习的技能转移到相关的环境。为了促进解决这个问题的研究,我们提出了因果结构和迁移学习在机器人操作环境中的一个基准Causal World。该环境是一个开源机器人平台的模拟,因此提供了仿真到现实迁移的可能性。任务包括从一组给定的块构建3D形状-灵感来自儿童如何学习构建复杂的结构。Causal World的关键优势在于,它提供了具有共同因果结构和潜在因素的此类任务的组合家族(包括,例如,机器人和物体质量、颜色、尺寸)。用户(或代理)可以干预所有因果变量,这允许对不同任务(或任务分布)的相似程度进行细粒度控制。因此,可以容易地定义期望难度水平的训练和评估分布,以特定形式的泛化为目标(例如,仅改变外观或物体质量)。此外,这种常见的参数化有助于通过在初始任务和目标任务之间进行插值来定义课程。虽然用户可以定义自己的任务分布,但我们提出了八种有意义的分布作为具体的基准,从简单到非常具有挑战性,所有这些都需要长期规划以及精确的低级运动控制。最后,我们为这些任务的一个子集提供了不同的培训课程和相应的评估协议的基线结果,验证了该基准中任务的可行性。

英文摘要:

Despite recent successes of reinforcement learning (RL), it remains a challenge for agents to transfer learned skills to related environments. To facilitate research addressing this problem, we propose CausalWorld, a benchmark for causal structure and transfer learning in a robotic manipulation environment. The environment is a simulation of an open-source robotic platform, hence offering the possibility of sim-to-real transfer. Tasks consist of constructing 3D shapes from a given set of blocks - inspired by how children learn to build complex structures. The key strength of CausalWorld is that it provides a combinatorial family of such tasks with common causal structure and underlying factors (including, e.g., robot and object masses, colors, sizes). The user (or the agent) may intervene on all causal variables, which allows for fine-grained control over how similar different tasks (or task distributions) are. One can thus easily define training and evaluation distributions of a desired difficulty level, targeting a specific form of generalization (e.g., only changes in appearance or object mass). Further, this common parametrization facilitates defining curricula by interpolating between an initial and a target task. While users may define their own task distributions, we present eight meaningful distributions as concrete benchmarks, ranging from simple to very challenging, all of which require long-horizon planning as well as precise low-level motor control. Finally, we provide baseline results for a subset of these tasks on distinct training curricula and corresponding evaluation protocols, verifying the feasibility of the tasks in this benchmark.

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。

↑