MIT
Lecture 17: Reinforcement Learning, Part 2
Data Science, Analytics & Computer TechnologyAIUser ExperienceMachine LearningComputer ScienceHealth & Medicine
Om kurset
In the first half, Prof. Sontag discusses how to evaluate different policies in causal inference and how it is related to reinforcement learning. In the second half, Dr. Barbra Dickerman talks about evaluating dynamic treatment strategies. Speakers: David Sontag, Barbra Dickerman Lecture 17: Evaluating Dynamic Treatment Strategies slides (PDF)