Skip to content
conftrace_
2024 ICML ICML 2024

Learning Cognitive Maps from Transformer Representations for Efficient Planning in Partially Observed Environments

Abstract

No abstract available. No abstract was captured for this paper when its proceedings were scraped - most often an older edition published without one online. How the corpus is built.

🌉 Interdisciplinary Bridge - Artificial Intelligence and Robotics

Authors

Antoine Dedieu, Wolfgang Lehrach, Guangyao Zhou, Dileep George, Miguel Lázaro-Gredilla

Topics

Deep Learning > Architectures > Transformers Robotics > Capabilities > Motion Planning Artificial Intelligence > Core AI > Large Language Models

Keywords

transformer cognitive map interpretable representation external solver partially observed environment in-context accuracy
Download PDF