Planning from Pixels in Atari with Learned Symbolic Representations

Andrea Dittadi, Frederik K. Drachmann, Thomas Bolander

Research output: Chapter in Book/Report/Conference proceedingArticle in proceedingsResearchpeer-review

4 Downloads (Pure)

Abstract

Width-based planning methods have been shown to yield state-of-the-art performance in the Atari 2600 domain using pixel input. One successful approach, RolloutIW, represents states with the B-PROST boolean feature set. An augmented version of RolloutIW, pi-IW, shows that learned features can be competitive with handcrafted ones for width-based search. In this paper, we leverage variational autoencoders (VAEs) to learn features directly from pixels in a principled manner, and without supervision. The inference model of the trained VAEs extracts boolean features from pixels, and RolloutIW plans with these features. The resulting combination outperforms the original RolloutIW and human professional play on Atari 2600 and drastically reduces the size of the feature set.
Original languageEnglish
Title of host publicationProceedings of 35th AAAI Conference on Artificial Intelligence
PublisherAssociation for the Advancement of Artificial Intelligence
Publication date2021
Pages4941-4949
ISBN (Print)978-1-57735-866-4
Publication statusPublished - 2021
Event35th AAAI Conference on Artificial Intelligence - Virtual Conference
Duration: 2 Feb 20219 Feb 2021

Conference

Conference35th AAAI Conference on Artificial Intelligence
LocationVirtual Conference
Period02/02/202109/02/2021
SeriesThirty-fifth Aaai Conference on Artificial Intelligence, Thirty-third Conference on Innovative Applications of Artificial Intelligence and the Eleventh Symposium on Educational Advances in Artificial Intelligence
Number6
Volume35
ISSN2374-3468

Fingerprint

Dive into the research topics of 'Planning from Pixels in Atari with Learned Symbolic Representations'. Together they form a unique fingerprint.

Cite this