AI-powered
podcast player
Listen to all your favourite podcasts with AI-powered features
Using Existing Knowledge in the Algorithms
There's going to be some trad of a between letting the algaritm learn by itself, versus giving it some structure. My impression is that for chess, and the lesson was, don't spoil the algoritm by teaching it human tricks because it'll learn faster just by playing against itselfye. So another weakness in curnei as we just don't know how to leverage existing knowledge. In some cases we do, but with emphasis on the right now, it is easier just to do brute force tan,. than to have a bunch of expert go players tell you stuff.