Reactor Learning

The dep c n technique couldn't find the optimal policy. So it's not so much saying that's a bad methodology, but a cautionary tale, i guess. With that in mind, do you have any advice for practitioners on how they can adopt hods or deploy the right policies? In real life, where there are complicated causal mechanisms and there are confounding variables which are unobservable, it's better for you to use your common sense and come up with a model. First, have an idea what a sensible policy, or what a sensible answer is. And then, even if you have models of the problem, you can use a kind of model base reinforcement learning to try and