How severe does this issue affect your experience of using Ray?
- High: It blocks me to complete my task.
Hi,
I want to implement Population Based Training with two different custom agents I wrote.
Is it possible to pass the two different trainables to the ray.tune.Tuner class at once?
I found these two examples:
- ray/rllib/examples/two_trainer_workflow.py at master · ray-project/ray · GitHub
- ray/rllib/examples/multi_agent_two_trainers.py at master · ray-project/ray · GitHub
However, it is not really clear to me if its possible to rewrite one of them using my custom implementations and pbt, not multi-agent learning.
Kind regards