Sjoerd van Steenkiste

Improving Generalization in Meta Reinforcement Learning using Learned Objectives

2019 · arXiv (Cornell University)

Biological evolution has distilled the experiences of many learners into the general learning algorithms of humans. Our novel meta reinforcement learning algorithm MetaGenRL is inspired by this process. MetaGenRL distills the experiences of many complex …

For human-like models, train on human-like tasks

2023 · Behavioral and Brain Sciences

Bowers et al. express skepticism about deep neural networks (DNNs) as models of human vision due to DNNs' failures to account for results from psychological research. We argue that to fairly assess DNNs, we must …