[HTML][HTML] Modelling cognitive flexibility with deep neural networks
K Sandbrink, C Summerfield - Current Opinion in Behavioral Sciences, 2024 - Elsevier
Highlights•We review recent advances in endowing deep RL systems with cognitive
flexibility.•Dual-process RL unifies habit-driven System I and deliberative System II …
flexibility.•Dual-process RL unifies habit-driven System I and deliberative System II …
[PDF][PDF] Understanding human meta-control and its pathologies using deep neural networks
In mammals, neurons in the medial prefrontal cortex respond to action prediction errors
(APEs). Here, using computational simulations with deep neural networks, we show the that …
(APEs). Here, using computational simulations with deep neural networks, we show the that …
Children prioritize purely exploratory actions in observe-vs.-bet tasks
E Yiu, K Sandbrink, A Gopnik - Intrinsically-Motivated and Open-Ended … - openreview.net
In reinforcement learning, agents often need to decide between selecting actions that are
familiar and have previously yielded positive results (exploitation), and seeking new …
familiar and have previously yielded positive results (exploitation), and seeking new …