DeepKoCo: Efficient latent planning with a task-relevant Koopman representation
Bas van der Heijden,Laura Ferranti,Jens Kober,Robert Babuška,Bas van der Heijden,Laura Ferranti,Jens Kober,Robert Babuška
This paper presents DeepKoCo, a novel modelbased agent that learns a latent Koopman representation from images. This representation allows DeepKoCo to plan efficiently using linear control methods, such as linear model predictive control. Compared to traditional agents, DeepKoCo learns taskrelevant dynamics, thanks to the use of a tailored lossy autoencoder network that allows DeepKoCo to learn la...
