论文标题
野生动物园：有想象力的安全和主动的机器人模仿学习
SAFARI: Safe and Active Robot Imitation Learning with Imagination
论文作者
论文摘要
模仿学习的主要问题之一是面对分发情况时，代理商的错误行为是错误的，而专家给出的一组演示套件没有涵盖。在这项工作中，我们通过引入一种新颖的积极学习和控制算法来解决这个问题。在培训期间，它允许代理商在满足这些分发情况时要求进一步的人类示威。在部署时，它使用行为克隆与基于模型的计划结合了无模型的表演，以减少状态分布的转移，并使用未来的状态重建作为状态熟悉度的测试。我们凭经验证明了这种方法如何通过收集更有信息的演示并最大程度地减少测试时的状态分布变化来提高一组操纵任务的性能。我们还展示了该方法如何使代理能够自主迅速，安全地预测故障。
One of the main issues in Imitation Learning is the erroneous behavior of an agent when facing out-of-distribution situations, not covered by the set of demonstrations given by the expert. In this work, we tackle this problem by introducing a novel active learning and control algorithm, SAFARI. During training, it allows an agent to request further human demonstrations when these out-of-distribution situations are met. At deployment, it combines model-free acting using behavioural cloning with model-based planning to reduce state-distribution shift, using future state reconstruction as a test for state familiarity. We empirically demonstrate how this method increases the performance on a set of manipulation tasks with respect to passive Imitation Learning, by gathering more informative demonstrations and by minimizing state-distribution shift at test time. We also show how this method enables the agent to autonomously predict failure rapidly and safely.
