arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2103.07732cs.ROcs.LG
收藏

错误感知策略学习:部分可观测动态环境中的Zero-Shot泛化

Error-Aware Policy Learning: Zero-Shot Generalization in Partially Observable Dynamic Environments

Georgia Institute of Technology(佐治亚理工学院);Stanford University(斯坦福大学)

Visak Kumar, Sehoon Ha, C. Karen Liu

摘要:

仿真提供了一种安全有效的方法来生成用于学习复杂机器人任务的有用数据。然而,匹配仿真和真实世界的动态可能是相当具有挑战性的,特别是对于具有大量未观察或不可测量的参数的系统,这些参数可能存在于机器人动态本身或机器人与之交互的环境中。我们引入了一种新的方法来解决这样一个模拟到真实的问题,通过制定能够适应新环境的政策,在zero-shot的方式。我们的方法的关键是一个错误感知政策(EAP),明确意识到在培训过程中不可观察的因素的影响。EAP将目标环境中的预测未来状态误差作为输入,该预测未来状态误差由与EAP同时训练的误差预测函数提供。我们验证了我们的方法上训练,以帮助人类用户从外部推动恢复辅助行走设备。我们表明,一个训练有素的EAP髋关节扭矩辅助设备可以转移到不同的人类代理人看不见的生物力学特性。此外,我们表明,我们的方法可以应用于其他标准的RL控制任务。

英文摘要:

Simulation provides a safe and efficient way to generate useful data for learning complex robotic tasks. However, matching simulation and real-world dynamics can be quite challenging, especially for systems that have a large number of unobserved or unmeasurable parameters, which may lie in the robot dynamics itself or in the environment with which the robot interacts. We introduce a novel approach to tackle such a sim-to-real problem by developing policies capable of adapting to new environments, in a zero-shot manner. Key to our approach is an error-aware policy (EAP) that is explicitly made aware of the effect of unobservable factors during training. An EAP takes as input the predicted future state error in the target environment, which is provided by an error-prediction function, simultaneously trained with the EAP. We validate our approach on an assistive walking device trained to help the human user recover from external pushes. We show that a trained EAP for a hip-torque assistive device can be transferred to different human agents with unseen biomechanical characteristics. In addition, we show that our method can be applied to other standard RL control tasks.

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。

↑