Search papers, labs, and topics across Lattice.
University of Aberdeen
3
0
4
MAGR-BB slashes hypothesis generation by orders of magnitude while achieving the same recognition accuracy as exhaustive search in multi-agent scenarios.
Imitation learning's obsession with perfect replay is a dead end; true progress lies in compositional adaptability, enabling agents to recombine learned behaviors in novel contexts without retraining.
Learn goal recognition from imperfect human behavior, and watch accuracy jump by 50% when the demonstrator is systematically biased.
