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
- Reward is not the optimization target — LessWronglesswrong.com
- A (Long) Peek into Reinforcement Learning | Lil'Loglilianweng.github.io
- Part 1: Key Concepts in RL - Spinning Up documentationspinningup.openai.com
- A Crash Course in the Neuroscience of Human Motivation — LessWronglesswrong.com
- Reward Is Not the Optimization Targetturntrout.com
- SuttonBartoIPRLBook2ndEd.pdfweb.stanford.edu
- Reinforcement learning - Wikipediaen.wikipedia.org
- Models Don't "Get Reward" — LessWronglesswrong.com
- Evolution as Backstop for Reinforcement Learning · Gwern.netgwern.net
- Data-driven equation discovery reveals nonlinear reinforcement learning in humanspmc.ncbi.nlm.nih.gov
- Deep Reinforcement Learning: Pong from Pixelskarpathy.github.io
- Life lessons from reinforcement learning - Jason Weijasonwei.net