Disparity between training and evaluation episodes

2 次查看（过去 30 天）
Ari
Ari 2025-5-1
编辑： Jacob Mathew 2025-5-13
I tried to re-train this DDPG control example using exact same configuration (except the max training episode set to 500) and this is the result I got:
It is quite different compared to the provided screen capture (below), despite the random seed has been fixed reproducibility purpose.
Why are there huge disparities between training and evaluation episodes on my training? Eventhough my training process was successful (evaluation statistic hit 2000), the last training episodes still couldn't match evaluation episodes. How to properly interpret this result? Is this normal?

请先登录，再回答此问题。

回答（1 个）

Jacob Mathew
Jacob Mathew 2025-5-13
编辑：Jacob Mathew 2025-5-13
Hey Ari,
I tried running the example on my end and got a different graph in the training compared to both what you have seen and the screenshot in the example guide. But my output was reproduceable across multiple runs of the example:
However, while the path taken during training does seem to vary, the results logged in the scope are inline with that the example expects, which showcases that the training was successful and predictions are in line:

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


版本

R2024b

Community Treasure Hunt

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

Start Hunting!

Translated by