How could I realize from the graph of "reinforcement learning episode manager" in DDPG or rlTD3Agent that the network is learning well?

1 次查看（过去 30 天）
ali kadkhodaei
ali kadkhodaei 2023-10-14
评论： Emmanouil Tzorakoleftherakis 2023-10-22
hi every body
im training a TG3Agent . when i see the "reinforcement learning episode manager" i dont realize that my network is learning well or not?
how can i found that? What are the signs of good learning from the chart?
my chart is below

请先登录，再回答此问题。

采纳的回答

Emmanouil Tzorakoleftherakis
You should be seeing the average reward curve going upwards (not monotonically) which is not the case here.
  2 个评论
ali kadkhodaei
ali kadkhodaei 2023-10-21
whats your advice for well learning ? increasing layers or nurons ?
using lstm layers instead of feauture layers?/
changing learning rate or gradient thereshhold?
or another things?
Emmanouil Tzorakoleftherakis
Emmanouil Tzorakoleftherakis 2023-10-22
Using LSTM layers instead of feature layers won't improve your performance unless the problem you are working on is a better fit for lstm policies. Usually improving the reward, exploration, and neural network architecture (layers/neurons etc) helps. But you also need to make sure the problem is set up correctly, i.e. you provide the appropriate observations so that the agent has enough information to learn.

请先登录，再进行评论。

更多回答（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

R2023a

Community Treasure Hunt

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

Start Hunting!

Translated by