0
$\begingroup$

I am interested in learning about hyper-parameter tuning for off-policy reinforcement learning (specifically DQN). Could someone point me to papers published or empirical observations in this area?

$\endgroup$

1 Answer 1

1
$\begingroup$

Yes and we can do it in a similar way we normally perform hyper-param optimization. See this paper from Google

In this framework we can also attempt to jerry-rig some of our classic algorithmic tuning techniques with better or worse success depending on the context.

$\endgroup$

You must log in to answer this question.

Not the answer you're looking for? Browse other questions tagged .