Re:AlphaGo Zero: Learning from scratch
by greysphere on Wednesday October 18, 2017 @04:47PM
(#15502876)
After digging a bit deeper into the paper, it seems a key part of the new scheme is the NN is trained to help guide a deep/sparse tree search (as opposed to TD-gammons fully exhaustive 2-ply search). It's somewhat surprising to me that the simple win/loss is a strong enough signal to train this very 'intermediate step' in the algorithm - a spectacular result! It begs the question what other heuristic based algorithms would be improved by replacing a hand rolled non-optimal heuristic function with a NN?
[ Parent
| on HN ]
It's estimating the probability of winning from the position based on what it has already seen. So basically it's a giant conditional probability distribution. Is it mistaken to interpret this as a bayesian network?