Modularity benefits reinforcement learning agents with competing homeostatic drives

no code implementations • 13 Apr 2022 • Zack Dulberg, Rachit Dubey, Isabel M. Berwian, Jonathan D. Cohen

The problem of balancing conflicting needs is fundamental to intelligence.

reinforcement-learning Reinforcement Learning (RL)

Connecting Context-specific Adaptation in Humans to Meta-learning

no code implementations • 27 Nov 2020 • Rachit Dubey, Erin Grant, Michael Luo, Karthik Narasimhan, Thomas Griffiths

This work connects the context-sensitive nature of cognitive control to a method for meta-learning with context-conditioned adaptation.

Meta-Learning

Investigating Human Priors for Playing Video Games

1 code implementation • ICML 2018 • Rachit Dubey, Pulkit Agrawal, Deepak Pathak, Thomas L. Griffiths, Alexei A. Efros

What makes humans so good at solving seemingly complex video games?

Decision Making

A rational analysis of curiosity

no code implementations • 11 May 2017 • Rachit Dubey, Thomas L. Griffiths

We present a rational analysis of curiosity, proposing that people's curiosity is driven by seeking stimuli that maximize their ability to make appropriate responses in the future.

What Makes an Object Memorable?

no code implementations • ICCV 2015 • Rachit Dubey, Joshua Peterson, Aditya Khosla, Ming-Hsuan Yang, Bernard Ghanem

We augment both the images and object segmentations from the PASCAL-S dataset with ground truth memorability scores and shed light on the various factors and properties that make an object memorable (or forgettable) to humans.

Object