Quantifying Generalization in Reinforcement Learning

Karl Cobbe
Karl Cobbe
Oleg Klimov
Oleg Klimov
Christopher Hesse
Christopher Hesse

international conference on machine learning, 2018.

Cited by: 108|Bibtex|Views22
EI
Other Links: dblp.uni-trier.de|academic.microsoft.com|arxiv.org

Abstract:

In this paper, we investigate the problem of overfitting in deep reinforcement learning. Among the most common benchmarks in RL, it is customary to use the same environments for both training and testing. This practice offers relatively little insight into an agentu0027s ability to generalize. We address this issue by using procedurally g...More

Code:

Data:

Full Text
Your rating :
0

 

Tags
Comments