Afterstates
A network that predicts how long you will live
Plans a neural evaluator that predicts remaining row rises so search can favor survival over immediate points.
Afterstates
Score the board a move leaves behind, and build training data in which every column the player could have chosen was measured.
Value the board after your move has resolved but before luck deals the next thing; then you never need to give the evaluator the action, and you never split a value seven ways by what comes next.
Read the primerApproaches using this technique
3 approaches, featured pages first. Each card is one theory of how to choose a column and what happened when it was tried.
Agent contextApproach directories in this group, by family
afterstate-learning
lifetime-objective
value-policy-learning