Zobrazeno 1 - 1
of 1
pro vyhledávání: '"P. Marlith Jaramillo"'
Publikováno v:
Artificial Intelligence Review. 52:2039-2059
Modeling policies in reproducing kernel Hilbert space (RKHS) offers a very flexible and powerful new family of policy gradient algorithms called RKHS policy gradient algorithms. They are designed to optimize over a space of very high or infinite dime