✳flâneur — a map of the web's best reading

Contrastive Representations for Temporal Reasoning

arxiv.org · 13,343 words · saved by 1 readers

This is experimental HTML to improve accessibility. We invite you to report rendering errors. Use Alt+Y to toggle on accessible reporting links and Alt+Shift+Y to toggle off. Learn more about this project and help improve conversions. In classical AI, perception relies on learning state-based representations, while planning — temporal reasoning over action sequences — is typically achieved through search. We study whether such reasoning can instead emerge from representations that capture both perceptual and temporal structure. We show that standard temporal contrastive learning, despite its popularity, often fails to capture temporal structure due to its reliance on spurious features. To address this, we introduce Contrastive Representations for Temporal Reasoning (CRTR), a method that uses a negative sampling scheme to provably remove these spurious features and facilitate temporal reasoning. CRTR achieves strong results on domains with complex temporal structure, such as Sokoban an

Contrastive Representations for Temporal Reasoning Alicja Ziarko 1 2 3 Michał Bortkiewicz 4 Michał Zawalski 1, 6 Benjamin Eysenbach 5 † \dagger Piotr Miłoś 1 3 † \dagger 1 University of Warsaw 2 IDEAS NCBR 3 IMPAN 4 Warsaw University of Technology 5 Princeton University 6 NVIDIA aa.ziarko@uw.edu.pl Abstract In classical AI, perception relies on learning state-based representations, while planning — temporal reasoning over action sequences — is typically achieved through search. We study whether such reasoning can instead emerge from representations that capture both perceptual and temporal str

Explore this link on the map →

related reading