Search papers, labs, and topics across Lattice.
Affiliation:
4
0
6
10
Strict safety guarantees in RL are now achievable without performance trade-offs, even with neural approximations.
Pragmatic-pedagogic reasoning enables robots to disambiguate human goals in one interaction, overcoming traditional alignment challenges in assistance games.
Adversarial RL unlocks robust control barrier functions for complex systems with black-box dynamics, moving beyond restrictive assumptions of control-affine systems and known uncertainty models.
Agents can rapidly adapt to individual and evolving user preferences by explicitly memorizing and acting on both pre- and post-action feedback.
