Q - learning reinforcement learning how to avoid the local optimal-CodePudding

Home > other > Q - learning reinforcement learning how to avoid the local optimal

Q - learning reinforcement learning how to avoid the local optimal

Time：10-05

Recently in the Q - learning to do routing planning, after is set at the beginning of the destination point according to the different path set bonus, but easy to fall into local optimum situation, even if the destination point of routing value is not the highest reward, but also can choose the path, request everyone a great god, and do you have any good ways to solve,

Page link：https//www.codepudding.com/other/52797.html

Prev:Interval the most value out of shape

Next:Keyerror tensorflow loaded. Meta data flow diagrams times

Tags：

Artificial intelligence technology

Links：
CodePudding