Learning to Navigate in Complex Environments

ICLR, Volume abs/1611.03673, 2017.

Cited by: 471|Bibtex|Views150
EI
Other Links: dblp.uni-trier.de|academic.microsoft.com|arxiv.org

Abstract:

Learning to navigate in complex environments with dynamic elements is an important milestone in developing AI agents. In this work we formulate the navigation question as a reinforcement learning problem and show that data efficiency and task performance can be dramatically improved by relying on additional auxiliary tasks to bootstrap le...More

Code:

Data:

Full Text
Your rating :
0

 

Tags
Comments