Episode Q0 increases exponentially

18 次查看（过去 30 天）
DAMODARAN B.K
DAMODARAN B.K 2021-2-16
编辑： DAMODARAN B.K 2021-2-17
Can anyone explain why episode Q0 in RL increases exponentially after convergence of reward to a suboptimal policy?

请先登录，再回答此问题。

回答（1 个）

Emmanouil Tzorakoleftherakis
Hello,
Please take a look at this answer for some suggestions. Normalizing observations, rewards, and actions can also help avoid situations like these.
Hope this helps

类别

在 Help Center 和 File Exchange 中查找有关 Training and Simulation 的更多信息

标签

产品

Community Treasure Hunt

Find the treasures in MATLAB Central and discover how the community can help you!

Start Hunting!

Translated by