flâneur

RL in Cognition - by Janet Shin - Janet's Substack

substack.com · 2,724 words · saved by 1 readers

The Development of Reinforcement Learning from a Cognitive Science Perspective

This semester, I’m taking a computational models of cognition course (Cogsci C131), and I highly recommend it! It’s an introductory course with very ambitious course material; we start from decision making (Signal Detection Theory, Drift Diffusion Models, Prospect Theory), to categorization and classification (prototype/exemplar models, perceptrons, Shepherds Universal law of Generalization), then to finally RL and working memory (RNNs, slots vs resource models, semantic networks). The thing that’s nice about this class is it’s as intensive as you want it to be. More than half the class ends…

saved by

related reading