arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2005.08114cs.CVcs.AIstat.ML
收藏

鲁棒可规划表示的互信息最大化

Mutual Information Maximization for Robust Plannable Representations

University of California, Berkeley(加州大学伯克利分校)

Yiming Ding, Ignasi Clavera, Pieter Abbeel

摘要:

将机器人技术的能力扩展到现实世界的复杂非结构化环境中,需要开发更好的感知系统,同时保持低样本复杂性。当处理高维状态空间时,当前的方法是基于重建目标的无模型或基于模型的。前者的样本效率低下构成了将其应用于现实世界的主要障碍。后者,虽然它们呈现低样本复杂度,但它们学习需要重建场景每个细节的潜在空间。在真实环境中,任务通常只代表场景的一小部分。在这种情况下,重建目标受到影响,因为它们捕获了所有不必要的组件。在这项工作中,我们提出了MIRO,一个基于基于模型的强化学习的信息理论表示学习算法。我们设计了一个潜在的空间,最大限度地提高了互信息与未来的信息,同时能够捕捉规划所需的所有信息。我们表明,我们的方法是更强大的比重建目标存在干扰和杂乱的场景

英文摘要:

Extending the capabilities of robotics to real-world complex, unstructured environments requires the need of developing better perception systems while maintaining low sample complexity. When dealing with high-dimensional state spaces, current methods are either model-free or model-based based on reconstruction objectives. The sample inefficiency of the former constitutes a major barrier for applying them to the real-world. The later, while they present low sample complexity, they learn latent spaces that need to reconstruct every single detail of the scene. In real environments, the task typically just represents a small fraction of the scene. Reconstruction objectives suffer in such scenarios as they capture all the unnecessary components. In this work, we present MIRO, an information theoretic representational learning algorithm for model-based reinforcement learning. We design a latent space that maximizes the mutual information with the future information while being able to capture all the information needed for planning. We show that our approach is more robust than reconstruction objectives in the presence of distractors and cluttered scenes

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。

↑