Deepracer Student League - What is happening when model training is "Evaluating"

0

Hello everyone,

I was wondering what is happening during the "Evaluating" phase during training for deepracer student. I see through the simulation video that across evaluation runs, there are still big differences in deepracer performance, so I was wondering if it is comparing different policies that it formed during training. I am using the PPO algorithm. Thanks in advance!

已提問 2 年前檢視次數 408 次
1 個回答
1

Here is documentation regarding the reward graph and how to interpret it.

In AWS DeepRacer, training happens in iterations. Each iteration is collection of <n> episodes, n is 20 by default for PPO, and is configurable and 1 for SAC, and is fixed. At the end of every iteration, latest model is saved as checkpoint for evaluation. Evaluation runs for 5 episodes (called Trials) and evaluation metrics (average completion percentage, average reward value) are saved. The current selection for criteria best model is at the maximum average completion percentage.

Hope this information is helpful for you.

AWS
已回答 2 年前

您尚未登入。 登入 去張貼答案。

一個好的回答可以清楚地回答問題並提供建設性的意見回饋,同時有助於提問者的專業成長。

回答問題指南