Hacker News new | ask | show | jobs
by greenflag 1111 days ago
Does anyone have high level guidance on when (deep) RL is worth pursuing for optimization (e.g. optimizing algorithm design) rather than other approaches (e.g genetic)?
2 comments

Less of a scale problem than a type problem usually in my experience.

My rule of thumb is when it’s easy to specify a reward function but infinite ways to traverse the action space - versus having a constrained state and action space (small n solution traversal pathways) and only a few possible paths to traverse.

Start with a planet-scale computer that makes the marginal cost of RL be nearly zero, and at the same time spend a lot of money on hashing and sorting so the micro-optimization pays off.