Contextualize Me – The Case for Context in Reinforcement Learning

authored by

Carolin Benjamins, Theresa Eimer, Frederik Günter Schubert, Aditya Mohan, Sebastian Döhler, André Biedenkapp, Bodo Rosenhahn, Frank Hutter, Marius Lindauer

Abstract

While Reinforcement Learning ( RL) has made great strides towards solving increasingly complicated problems, many algorithms are still brittle to even slight environmental changes. Contextual Reinforcement Learning (cRL) provides a framework to model such changes in a principled manner, thereby enabling flexible, precise and interpretable task specification and generation. Our goal is to show how the framework of cRL contributes to improving zero-shot generalization in RL through meaningful benchmarks and structured reasoning
about generalization tasks. We confirm the insight that optimal behavior in cRL requires context information, as in other related areas of partial observability. To empirically validate this in the cRL framework, we provide various context-extended versions of common RL environments. They are part of the first benchmark library, CARL, designed for generalization based on cRL extensions of popular benchmarks, which we propose as a testbed to further study general agents. We show that in the contextual setting, even simple RL environments become challenging - and that naive solutions are not enough to generalize across complex context spaces.

Organisation(s)

Machine Learning Section
Institute of Information Processing
Automatic Image Interpretation Section

External Organisation(s)

University of Freiburg

Type

Article

Journal

Transactions on Machine Learning Research

Volume

2023

ISSN

2835-8856

Publication date

05.06.2023

Publication status

E-pub ahead of print

Peer reviewed

Yes

Electronic version(s)

https://doi.org/10.48550/arXiv.2202.04500 (Access: Open)
https://openreview.net/forum?id=Y42xVBQusn&referrer=%5Bthe%20profile%20of%20Frank%20Hutter%5D(%2Fprofile%3Fid%3D~Frank_Hutter1) (Access: Open)