Emma Brunskill Emma Brunskill @EmmaBrunskill

Batch off-policy policy evaluation in RL is particularly important in healthcare/education/recommendation systems. Omer will describe adaptively combining models to minimize value estimate error. jt w/Liu, Sussex, & Doshi-Velez Talk @ 4:40pm, @ Rm 104 . Poster 116. #ICML2019

5:28 PM - 12 Jun 19
Previous Video
Stanford CS234: Reinforcement Learning | Winter 2019 | Lecture 8 - Policy Gradient I
Stanford CS234: Reinforcement Learning | Winter 2019 | Lecture 8 - Policy Gradient I

Professor Emma Brunskill, Stanford University http://onlinehub.stanford.edu/ Professor Emma Brunskill Ass...

Next Video
Stanford CS234: Reinforcement Learning | Winter 2019 | Lecture 9 - Policy Gradient II
Stanford CS234: Reinforcement Learning | Winter 2019 | Lecture 9 - Policy Gradient II

Professor Emma Brunskill, Stanford University http://onlinehub.stanford.edu/ Professor Emma Brunskill Ass...