Nathan Gavenski

2 accepted papers

2026

Online Goal Recognition Using Path Signature and Dynamic Time Warping

Douglas Tesch, Nathan Gavenski, Leonardo Rosa Amado, Odinaldo Rodrigues, Felipe Meneguzzi

IJCAI 2026

Online goal recognition in continuous domains poses two central challenges: efficiently encoding large trajectories and effectively comparing them. Recent work addresses these challenges by using custom state-space representations and metrics to compare observations against hypotheses. However, thes

Cited by 0 Scholar ↗

2025

Quantifying Generalisation in Imitation Learning

Nathan Gavenski, Odinaldo Rodrigues

NeurIPS 2025poster

Imitation learning benchmarks often lack sufficient variation between training and evaluation, limiting meaningful generalisation assessment. We introduce Labyrinth, a benchmarking environment designed to test generalisation with precise control over structure, start and goal positions, and task co…

Cited by 0 Source ↗Scholar ↗