Search papers, labs, and topics across Lattice.
3
0
6
QVIRL achieves robust apprenticeship learning from raw pixel data while quantifying uncertainty, a breakthrough for safety-critical AI applications.
Auxiliary data can dramatically enhance constrained Bayesian Optimization, even when weakly correlated, leading to superior exploration and solution identification.
Hierarchical policies aren't just for horizon reduction; they can unlock powerful state-space abstraction for dramatic gains in offline goal-conditioned RL.
