Saved in:
Bibliographic Details
Main Authors: Carvalho, Wilka, Tomov, Momchil S., de Cothi, William, Barry, Caswell, Gershman, Samuel J.
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2402.06590
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910522010501120
author Carvalho, Wilka
Tomov, Momchil S.
de Cothi, William
Barry, Caswell
Gershman, Samuel J.
author_facet Carvalho, Wilka
Tomov, Momchil S.
de Cothi, William
Barry, Caswell
Gershman, Samuel J.
contents Adaptive behavior often requires predicting future events. The theory of reinforcement learning prescribes what kinds of predictive representations are useful and how to compute them. This paper integrates these theoretical ideas with work on cognition and neuroscience. We pay special attention to the successor representation (SR) and its generalizations, which have been widely applied both as engineering tools and models of brain function. This convergence suggests that particular kinds of predictive representations may function as versatile building blocks of intelligence.
format Preprint
id arxiv_https___arxiv_org_abs_2402_06590
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Predictive representations: building blocks of intelligence
Carvalho, Wilka
Tomov, Momchil S.
de Cothi, William
Barry, Caswell
Gershman, Samuel J.
Artificial Intelligence
Machine Learning
Adaptive behavior often requires predicting future events. The theory of reinforcement learning prescribes what kinds of predictive representations are useful and how to compute them. This paper integrates these theoretical ideas with work on cognition and neuroscience. We pay special attention to the successor representation (SR) and its generalizations, which have been widely applied both as engineering tools and models of brain function. This convergence suggests that particular kinds of predictive representations may function as versatile building blocks of intelligence.
title Predictive representations: building blocks of intelligence
topic Artificial Intelligence
Machine Learning
url https://arxiv.org/abs/2402.06590