Learning World Graphs to Accelerate Hierarchical Reinforcement Learning

First published at 08:03 UTC on September 9th, 2019.

The goal of hierarchical reinforcement learning is to divide a task into different levels of coarseness with the top-level agent planning only over a high-level view of the world and each subsequent layer having a more detailed view. This paper pr...

CategoryScience & Technology
SensitivityNormal - Content that is suitable for ages 13+