• NPB/NSC 287A-Topics in Theoretical Neuroscience: Reinforcement Learning!

Reinforcement learning is both a powerful theory of animal learning and engineering control, and a technological breakthrough that has led to stunning advances in machine learning. Learn the foundations of reinforcement learning theory as we focus on core principles and methods from the classic text Reinforcement Learning. Topics will include:

-Markov decision processes

-Dynamic programming

-Temporal difference learning

-Optimal policy approximations

Credit, Contact info: 2 units, credit/non; for course questions,

email instructor Mark Goldman, msgoldman@ucdavis.edu.

CRN: 42845 (for NPB 287A); 43010 (for NSC 287A)

Time: Thursdays, 9:00-11:00am*; online only format

  • ATM 120. Atmospheric Thermodynamics and Cloud Physics (A. Igel)
  • ATM 245. Climate Change, Water and Society (Monier)
  • ATM 298. Literature in Climate Dynamics (Yang)
  • ATM 270. Tropical Meteorology (Yang)
  • ECL/PBG 231: Mathematical Methods in Population BiologyDescription: This course is an introduction to mathematical methods used in theoretical population biology. Population biology, here, refers to any area of the biological sciences focusing on population-level processes including areas in demography, conservation biology, ecology, epidemiology, evolution, and population genetics. The mathematical topics covered will include scalar and multivariate difference/differential equations, matrix and integral projection models, Markov chains, random walks, and stochastic difference equations.Link to Syllabus: https://schreiber.faculty.ucdavis.edu/wp-content/uploads/sites/568/2020/09/231-syllabus.pdf