M
Matthew Botvinick
Researcher at University College London
Publications - 249
Citations - 57443
Matthew Botvinick is an academic researcher from University College London. The author has contributed to research in topics: Reinforcement learning & Computer science. The author has an hindex of 77, co-authored 224 publications receiving 48206 citations. Previous affiliations of Matthew Botvinick include Princeton University & University of Pennsylvania.
Papers
More filters
Proceedings Article
General-purpose, long-context autoregressive modeling with Perceiver AR
Curtis Hawthorne,Andrew Jaegle,Catalina Cangea,Sebastian Borgeaud,Charlie Nash,Mateusz Malinowski,Sander Dieleman,Oriol Vinyals,Matthew Botvinick,Ian Simon,Hannah R. Sheahan,Neil Zeghidour,Jean-Baptiste Alayrac,Joao Carreira,Jesse Engel +14 more
TL;DR: Perceiver AR is developed, an modality-agnostic architecture which uses cross-attention to map long-range inputs to a small number of latents while also maintaining end-to-end causal masking, enabling practical long-context density estimation without the need for hand-crafted sparsity patterns or memory mechanisms.
Book ChapterDOI
Divide and Conquer: Hierarchical Reinforcement Learning and Task Decomposition in Humans
Carlos Diuk,Anna C. Schapiro,Natalia I. Córdova,José J. F. Ribas-Fernandes,Yael Niv,Matthew Botvinick +5 more
TL;DR: This chapter reviews two results that show the existence of neural correlates to key predictions from HRL, and focuses on one aspect of this work, which deals with the question of how action hierarchies are initially established.
Journal ArticleDOI
Toward an integrated account of object and action selection: A computational analysis and empirical findings from reaching-to-grasp and tool-use
TL;DR: A computational model of object and action selection is developed and analyzed, established through a series of simulations, that the impact of distractor objects on reaching times can vary depending on the nature of the current action plan.
Journal ArticleDOI
Intuitive physics learning in a deep-learning model inspired by developmental psychology
TL;DR: In this paper , a deep learning system was proposed to learn intuitive physics directly from visual data, inspired by studies of visual cognition in children, which can learn a diverse set of physical concepts, which depends critically on object-level representations, consistent with findings from developmental psychology.
Journal ArticleDOI
Representing task context: proposals based on a connectionist model of action
Matthew Botvinick,David C. Plaut +1 more
TL;DR: This model's implications for understanding task representation are considered, considering the implications of the account for two influential concepts: (1) cognitive underspecification, the idea that task representations may be imprecise or vague, especially in contexts where errors occur, and (2) information-sharing,The idea that closely related operations rely on common sets of internal representations.