Unsupervised Representation Learning in Deep Reinforcement Learning: A Review

Nicolò Botteghi, Mannes Poel, Christoph Brune

Research output: Working paperPreprintAcademic

107 Downloads (Pure)

Abstract

This review addresses the problem of learning abstract representations of the measurement data in the context of Deep Reinforcement Learning (DRL). While the data are often ambiguous, high-dimensional, and complex to interpret, many dynamical systems can be effectively described by a low-dimensional set of state variables. Discovering these state variables from the data is a crucial aspect for improving the data efficiency, robustness and generalization of DRL methods, tackling the \textit{curse of dimensionality}, and bringing interpretability and insights into black-box DRL. This review provides a comprehensive and complete overview of unsupervised representation learning in DRL by describing the main Deep Learning tools used for learning representations of the world, providing a systematic view of the method and principles, summarizing applications, benchmarks and evaluation strategies, and discussing open challenges and future directions.
Original languageEnglish
PublisherArXiv.org
Pages1
Number of pages51
DOIs
Publication statusPublished - 27 Aug 2022

Keywords

  • Reinforcement learning
  • Unsupervised representation learning
  • Dynamical systems

Fingerprint

Dive into the research topics of 'Unsupervised Representation Learning in Deep Reinforcement Learning: A Review'. Together they form a unique fingerprint.

Cite this