Conformal Policy Learning for Sensorimotor Control Under Distribution Shifts.
CoRR(2023)
摘要
This paper focuses on the problem of detecting and reacting to changes in the
distribution of a sensorimotor controller's observables. The key idea is the
design of switching policies that can take conformal quantiles as input, which
we define as conformal policy learning, that allows robots to detect
distribution shifts with formal statistical guarantees. We show how to design
such policies by using conformal quantiles to switch between base policies with
different characteristics, e.g. safety or speed, or directly augmenting a
policy observation with a quantile and training it with reinforcement learning.
Theoretically, we show that such policies achieve the formal convergence
guarantees in finite time. In addition, we thoroughly evaluate their advantages
and limitations on two compelling use cases: simulated autonomous driving and
active perception with a physical quadruped. Empirical results demonstrate that
our approach outperforms five baselines. It is also the simplest of the
baseline strategies besides one ablation. Being easy to use, flexible, and with
formal guarantees, our work demonstrates how conformal prediction can be an
effective tool for sensorimotor learning under uncertainty.
更多查看译文
关键词
sensorimotor control,learning,conformal
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要