Reinforcement Learning

Explore the fundamentals of reinforcement learning and its applications in psychology and neuroscience through this comprehensive tutorial led by Prof. Sam Gershman from Harvard University. Delve into key concepts such as Pavlovian conditioning, associative learning theory, and temporal difference learning. Engage in hands-on exercises to understand how simple algorithms explain animal learning and dopamine neuron firing. Access supplementary materials, including slides, references, and code, to enhance your learning experience. Gain insights into probabilistic interpretations, the Kalman filter, sequential decision problems, and the behavioral implications of temporal difference learning.

Intro
Pavlovian conditioning
Associative learning theory
Examples
Probabilistic interpretation
What's missing?
The Kalman filter
Some intuitions
Backward blocking
Modeling recovery phenomena
Sequential decision problems
Long-term reward prediction
Prediction errors
Temporal difference learning
Stimulus representation
Behavioral implications of TD
Dopamine