Search papers, labs, and topics across Lattice.
4
0
3
7
Tailored airflow profiles for UAVs can now be generated on-the-fly, dramatically improving flight performance and experimental efficiency.
Bridging the gap between reinforcement learning and control theory could unlock new synergies in optimizing unknown dynamical systems.
Q-learning can provably converge to optimal policies in non-Markovian environments, even with hard state aggregation, using a simple action-commitment strategy.
Zeroth-order optimization stability depends on the *entire* Hessian spectrum, not just the largest eigenvalue like first-order methods, offering a new perspective on implicit regularization.
