What Are the Statistical Limits of Offline Reinforcement Learning With Function Approximation?
Simons Institute for the Theory of Computing
0:00 / 0:00
What Are the Statistical Limits of Offline Reinforcement Learning With Function Approximation?
1 470 просмотров · Трансляция закончилась 5 лет назад
Simons Institute for the Theory of Computing
76,7 тыс. подписчиков
1 470 просмотров · Трансляция закончилась 5 лет назад
Sham Kakade (University of Washington & Microsoft Research)
https://simons.berkeley.edu/talks/low...
Mathematics of Online Decision Making
