arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2005.03770cs.LGcs.CVstat.ML
收藏

基于深潜高斯过程动力学的图像规划

Planning from Images with Deep Latent Gaussian Process Dynamics

Max Planck Institute for Intelligent Systems(马克斯·普朗克智能系统研究所);Technical University of Munich(慕尼黑工业大学)

Nathanael Bosch, Jan Achterhold, Laura Leal-Taixé, Jörg Stückler

摘要:

规划是一种强有力的方法来控制已知的环境动态问题。在未知的环境中,智能体需要学习系统动力学模型,以使规划适用。当底层状态只能通过图像间接观察时,这尤其具有挑战性。我们建议学习一个深度潜在高斯过程动力学(DLGPD)模型,该模型从环境与视觉观察的交互中学习低维系统动力学。该方法使用神经网络从观测值推断潜在状态表示,并使用高斯过程在学习的潜在空间中对系统动态进行建模。模型的所有部分可以通过优化图像空间中过渡可能性的下限来联合训练。我们评估所提出的方法上的钟摆摆动的任务,同时使用学习的动力学模型规划在潜在的空间,以解决控制问题。我们还证明,我们的方法可以快速适应一个受过训练的代理在系统动态的变化,从几个推出。我们将我们的方法与最先进的纯深度学习方法进行比较,并展示了将高斯过程与深度学习相结合以提高数据效率和迁移学习的优势。

英文摘要:

Planning is a powerful approach to control problems with known environment dynamics. In unknown environments the agent needs to learn a model of the system dynamics to make planning applicable. This is particularly challenging when the underlying states are only indirectly observable through images. We propose to learn a deep latent Gaussian process dynamics (DLGPD) model that learns low-dimensional system dynamics from environment interactions with visual observations. The method infers latent state representations from observations using neural networks and models the system dynamics in the learned latent space with Gaussian processes. All parts of the model can be trained jointly by optimizing a lower bound on the likelihood of transitions in image space. We evaluate the proposed approach on the pendulum swing-up task while using the learned dynamics model for planning in latent space in order to solve the control problem. We also demonstrate that our method can quickly adapt a trained agent to changes in the system dynamics from just a few rollouts. We compare our approach to a state-of-the-art purely deep learning based method and demonstrate the advantages of combining Gaussian processes with deep learning for data efficiency and transfer learning.

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。

↑