arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2107.05686cs.LGstat.ML
收藏

预训练表示在强化学习Agent的OOD泛化中的作用

The Role of Pretrained Representations for the OOD Generalization of Reinforcement Learning Agents

Max Planck Institute for Intelligent Systems(马克斯·普朗克智能系统研究所);Technical University of Denmark(丹麦技术大学);Amazon Lablets(亚马逊实验室);Google Brain(谷歌大脑);KTH Stockholm(斯德哥尔摩皇家理工学院)

Andrea Dittadi, Frederik Träuble, Manuel Wüthrich, Felix Widmaier, Peter Gehler, Ole Winther, Francesco Locatello, Olivier Bachem, Bernhard Schölkopf, Stefan Bauer

摘要:

在现实世界的环境中,构建样本效率高的代理来推广分布外(OOD)仍然是实现更高层次认知的道路上一个基本的未解决的问题。一种特别有前途的方法是从我们世界的低维预训练表示开始,这应该有助于有效的下游学习和泛化。通过在模拟机器人设置上训练240个表示和超过10,000个强化学习(RL)策略,我们评估了预训练的基于VAE的表示的不同属性在多大程度上影响下游代理的OOD泛化。我们观察到,许多代理人是令人惊讶的强大的现实分布偏移,包括具有挑战性的模拟真实的情况下。此外,我们发现,一个简单的下游代理任务的泛化性能可靠地预测我们的RL代理的泛化性能在广泛的OOD设置。因此,这种代理任务可以用于选择预训练的表示,这将导致代理泛化。

英文摘要:

Building sample-efficient agents that generalize out-of-distribution (OOD) in real-world settings remains a fundamental unsolved problem on the path towards achieving higher-level cognition. One particularly promising approach is to begin with low-dimensional, pretrained representations of our world, which should facilitate efficient downstream learning and generalization. By training 240 representations and over 10,000 reinforcement learning (RL) policies on a simulated robotic setup, we evaluate to what extent different properties of pretrained VAE-based representations affect the OOD generalization of downstream agents. We observe that many agents are surprisingly robust to realistic distribution shifts, including the challenging sim-to-real case. In addition, we find that the generalization performance of a simple downstream proxy task reliably predicts the generalization performance of our RL agents under a wide range of OOD settings. Such proxy tasks can thus be used to select pretrained representations that will lead to agents that generalize.

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。

↑