April 24, 2024, 4:42 a.m. | Anson Lei, Frederik Nolte, Bernhard Sch\"olkopf, Ingmar Posner

cs.LG updates on arXiv.org arxiv.org

arXiv:2404.15109v1 Announce Type: new
Abstract: We present COmpetitive Mechanisms for Efficient Transfer (COMET), a modular world model which leverages reusable, independent mechanisms across different environments. COMET is trained on multiple environments with varying dynamics via a two-step process: competition and composition. This enables the model to recognise and learn transferable mechanisms. Specifically, in the competition phase, COMET is trained with a winner-takes-all gradient allocation, encouraging the emergence of independent mechanisms. These are then re-used in the composition phase, where COMET …

abstract arxiv comet competition cs.lg dynamics environments independent learn modular multiple process transfer type via world world model world models

Software Engineer for AI Training Data (School Specific)

@ G2i Inc | Remote

Software Engineer for AI Training Data (Python)

@ G2i Inc | Remote

Software Engineer for AI Training Data (Tier 2)

@ G2i Inc | Remote

Data Engineer

@ Lemon.io | Remote: Europe, LATAM, Canada, UK, Asia, Oceania

Artificial Intelligence – Bioinformatic Expert

@ University of Texas Medical Branch | Galveston, TX

Lead Developer (AI)

@ Cere Network | San Francisco, US