A Simple Guard for Learned Optimizers

no code implementations • 28 Jan 2022 • Isabeau Prémont-Schwarz, Jaroslav Vítků, Jan Feyereisl

Even if learned optimizers (L2Os) eventually outpace hand-crafted ones in practice however, they are still not provably convergent and might fail out of distribution.

ToyArchitecture: Unsupervised Learning of Interpretable Models of the World

1 code implementation • 20 Mar 2019 • Jaroslav Vítků, Petr Dluhoš, Joseph Davidson, Matěj Nikl, Simon Andersson, Přemysl Paška, Jan Šinkora, Petr Hlubuček, Martin Stránský, Martin Hyben, Martin Poliak, Jan Feyereisl, Marek Rosa

Research in Artificial Intelligence (AI) has focused mostly on two extremes: either on small improvements in narrow AI domains, or on universal theoretical frameworks which are usually uncomputable, incompatible with theories of biological intelligence, or lack practical implementations.

Model-based Reinforcement Learning