Article

SPAR: Search-trained Push Action Ranker Improves Navigation Efficiency Among Movable Obstacles

The paper proposes SPAR (Search-trained Push Action Ranker), which learns to rank push primitives from simulated search results to alleviate the exponential growth of candidate action sequences with sequence length in Navigation Among Movable Obstacles (NAMO).

Part of the event: SPAR: Using Search-Trained Rankers to Improve Push Action Search Efficiency

This page provides a summary and source link only.