Is it possible to change RL action values under certain conditions?

1 次查看（过去 30 天）
black_cat
black_cat 2021-5-18
编辑： black_cat 2021-5-20
I want my agent to output a target value, but in certain situations (reward drops dramatically), I would want the agent to look for a better solution by letting him change the target value. I tried to use initial condition block in order to use the target value in the first place. However, my agent (PPO) always outputs an average value after some training episodes.
  5 个评论
显示 3更早的评论
black_cat
black_cat 2021-5-20
编辑：black_cat 2021-5-20
I've tried to create a minimal version that illustrates my problem. Here, I'm outputing numbers from 1-3. I hope it's more understandable that way.
black_cat
black_cat 2021-5-20
编辑：black_cat 2021-5-20
Okay, even though the attached example is supposed to be easy to understand, I think I'm able to put my problem in simple terms now:
  • I'm training my agent to output 3 discrete values (1, 2, 3)
  • I punish him for not outputing my target value
  • My target value is 1 for 50% of the time and 3 for the other 50% of the time
When training the agent is done (no matter which one, they all act the same in this case), it will output 1 or 3. For 100% of the time. It's not changing the output values at all. It's just using one. This is my problem.

请先登录，再进行评论。

请先登录，再回答此问题。

回答（0 个）

类别

在 Help Center 和 File Exchange 中查找有关 Reinforcement Learning 的更多信息

标签

产品


版本

R2020b

Community Treasure Hunt

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

Start Hunting!

Translated by