IMPROVING GENERALIZATION IN META REINFORCEMENT LEARNING USING LEARNED OBJECTIVES

Louis Kirsch, Sjoerd van Steenkiste, Jürgen Schmidhuber

Research output: Contribution to conferencePaperpeer-review

43 Scopus citations

Abstract

Biological evolution has distilled the experiences of many learners into the general learning algorithms of humans. Our novel meta reinforcement learning algorithm MetaGenRL is inspired by this process. MetaGenRL distills the experiences of many complex agents to meta-learn a low-complexity neural objective function that decides how future individuals will learn. Unlike recent meta-RL algorithms, MetaGenRL can generalize to new environments that are entirely different from those used for meta-training. In some cases, it even outperforms human-engineered RL algorithms. MetaGenRL uses off-policy second-order gradients during meta-training that greatly increase its sample efficiency.

Original languageEnglish (US)
StatePublished - 2020
Event8th International Conference on Learning Representations, ICLR 2020 - Addis Ababa, Ethiopia
Duration: Apr 30 2020 → …

Conference

Conference8th International Conference on Learning Representations, ICLR 2020
Country/TerritoryEthiopia
CityAddis Ababa
Period04/30/20 → …

ASJC Scopus subject areas

  • Education
  • Linguistics and Language
  • Language and Linguistics
  • Computer Science Applications

Fingerprint

Dive into the research topics of 'IMPROVING GENERALIZATION IN META REINFORCEMENT LEARNING USING LEARNED OBJECTIVES'. Together they form a unique fingerprint.

Cite this