Hacker Newsnew | past | comments | ask | show | jobs | submitlogin

Wasn't the breakthrough with AlphaGo that it doesn't consider every board combination in the future? Because that there are too many combinations?


Yes, but pruning (not considering everything) is as old as game tree search. Previous Go AIs used MCTS as well. What's new in AlphaGo is a more sophisticated approach to scoring game boards - policy networks that help the AI prune even more aggressively, and a value network that's used to "guess" the winner in lieu of searching to endgame. Note that guessing the winner is just a special case of an evaluation function. For any game, if you could consistently search to the end, your evaluation function is always a -1/1 corresponding to lose/win. AlphaGo is still using MCTS - just a more sophisticated form.




Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: