A map-conditioned hypermodel plus MuZero-style planning lets an agent navigate novel maze layouts in zero-shot from an abstract top-down map.
Learning exploration policies for navigation
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2024 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Learning to Navigate in Mazes with Novel Layouts using Abstract Top-down Maps
A map-conditioned hypermodel plus MuZero-style planning lets an agent navigate novel maze layouts in zero-shot from an abstract top-down map.