Search papers, labs, and topics across Lattice.
3
0
5
BPG reduces forgetting to an impressive 0.22% while achieving state-of-the-art accuracy in domain incremental learning.
RL agents can learn more robust vision-and-language navigation policies by exploring diverse trajectories and comparing their performance, even without expert demonstrations or value networks.
Achieve stable continual learning without catastrophic forgetting by fixing classifier weights to an Equiangular Tight Frame and aligning features geometrically.
