发帖
雷达卡
Logarithmic Regret for Reinforcement Learning with Linear Function
Approximation
Jiafan He 1 Dongruo Zhou 1 Quanquan Gu 1
Abstract A common approach to cope with high-dimensional state
Reinforcement learning (RL) with linear function and action spaces is to utilize function approximation such
approximation has received increasing attention as linear functions or neural networks to map states and
recently. How ...
京公网安备 11010802022788号
