论文标题
在嘈杂条件下基于模型的基于模型的适应
Few-shot model-based adaptation in noisy conditions
论文作者
论文摘要
在机器人技术中模拟传输的背景下，几乎没有射击适应性是一个具有挑战性的问题，需要安全且内容丰富的数据收集。在物理系统中，可能会通过域噪声提出其他挑战，该域噪声几乎存在于所有现实世界应用中。在本文中，我们建议使用基于不确定性的Kalman滤波器基于神经网络体系结构在嘈杂条件下对动态模型进行几次适应。我们表明，明确解决域噪声的提议方法可以改善BlackBox适应LSTM基线的几乎没有射击的适应性误差，并在一种无模型的上式加固学习方法上，试图同时学习适应性和信息性的策略。所提出的方法还可以通过分析适应过程中和之后模型的隐藏状态来进行系统分析。
Few-shot adaptation is a challenging problem in the context of simulation-to-real transfer in robotics, requiring safe and informative data collection. In physical systems, additional challenge may be posed by domain noise, which is present in virtually all real-world applications. In this paper, we propose to perform few-shot adaptation of dynamics models in noisy conditions using an uncertainty-aware Kalman filter-based neural network architecture. We show that the proposed method, which explicitly addresses domain noise, improves few-shot adaptation error over a blackbox adaptation LSTM baseline, and over a model-free on-policy reinforcement learning approach, which tries to learn an adaptable and informative policy at the same time. The proposed method also allows for system analysis by analyzing hidden states of the model during and after adaptation.
