22 citations · 63 across the 12 of their papers we have counts for
4 papers · 1 filter
Modularity benefits reinforcement learning agents with competing homeostatic drives
Zack Dulberg, Rachit Dubey, Isabel M. Berwian +1
The problem of balancing conflicting needs is fundamental to intelligence. Standard reinforcement learning algorithms maximize a scalar reward, which requires combining different o…
A Self-Supervised Framework for Function Learning and Extrapolation
Simon N. Segert, Jonathan D. Cohen
Understanding how agents learn to generalize -- and, in particular, to extrapolate -- in high-dimensional, naturalistic environments remains a challenge for both machine learning a…
Meta-Learning of Structured Task Distributions in Humans and Machines
Sreejan Kumar, Ishita Dasgupta, Jonathan D. Cohen +2
In recent years, meta-learning, in which a model is trained on a family of tasks (i.e. a task distribution), has emerged as an approach to training neural networks to perform tasks…
Navigating the Trade-Off between Multi-Task Learning and Learning to Multitask in Deep Neural Networks
Sachin Ravi, Sebastian Musslick, Maia Hamin +2
The terms multi-task learning and multitasking are easily confused. Multi-task learning refers to a paradigm in machine learning in which a network is trained on various related ta…