The Hard-Exploration Problem The “hard-exploration” problem refers to exploration in an environment with very sparse or even deceptive reward. It is difficult because random exploration in such scenarios can rarely discover successful states or obtain meaningful feedback.
In machine learning research, one often needs to run many experiments in parallel e.g. hyperparameter search. In this post, we gather some useful tricks in one place for better productivity.
We all know that a healthy lifestyle could enable us to work much more efficiently and keep being creative. For machine learning researchers, a good health management could be even more important because many of us often have to sit quite long time on the chair.