Search papers, labs, and topics across Lattice.
3
0
3
2
Achieving up to 70.6% fewer samples for optimal closed-loop performance could revolutionize how we approach online adaptation in reinforcement learning.
Robots can recover from dynamic disturbances five times faster than traditional methods, revolutionizing real-time policy adaptation.
Quadrotors can now fly significantly faster and more reliably through complex environments by explicitly optimizing trajectories for both speed and visual perception quality.
