English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

State representation learning, or the ability to capture latent generativefactors of an environment, is crucial for building intelligent agents that canperform a wide variety of tasks. Learning such representations withoutsupervision from rewards is a challenging open problem. We introduce a methodthat learns state representations by maximizing mutual information acrossspatially and temporally distinct features of a neural encoder of theobservations. We also introduce a new benchmark based on Atari 2600 games wherewe evaluate representations based on how well they capture the ground truthstate variables. We believe this new framework for evaluating representationlearning models will be crucial for future representation learning research.Finally, we compare our technique with other state-of-the-art generative andcontrastive representation learning methods. The code associated with this workis available at https://github.com/mila-iqia/atari-representation-learning

Unsupervised State Representation Learning in Atari