Algo.evaluate() vs auto eval

How severe does this issue affect your experience of using Ray?

  • Medium: It contributes to significant difficulty to complete my task, but I can work around it.

In the RLLib documentation it states that the proper way to perform evaluation after training is with: algo.evaluate(). However, you need to define the evaluation_interval in the Algorithm’s configuration which indicates that it will automatically perform evaluation after a certain number of training intervals.

Is there a way for me to only perform evaluation via calling it (algo.evaluate()) instead of having it run at an evaluation_interval?