Bas van der Heijden

DeepKoCo: Efficient latent planning with a task-relevant Koopman representation

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…