However the quicker the game is played, the more games AlphaZero sees, the more different situations it is exposed to, and the more it can learn. There is a trade-off here: one might think that AlphaZero could learn more by playing slower, high-quality games. Read more: This is how Google's DeepMind crushed puny humans at StarCraft
For example, AlphaZero trains by playing vast numbers of lightning-fast games (40 milliseconds a move) against itself at a very shallow search depth. There are many unexpected aspects to this. In our book Game Changer: AlphaZero’s Groundbreaking Chess Strategies and the Promise of AI we work with the DeepMind technical team to explain how AlphaZero’s construction and training has led to its creative and intuitive style. We particularly noticed how alert AlphaZero was to the danger of landing in a passive position without prospects and how driven it was to avoid this scenario. Its strength compared with traditional engines wasn’t necessarily in calculation-heavy positions but rather in intricate positions in which a mixture of calculation, positional insight and long-term planning was required. “AlphaZero find us a path!” became our standard cry during the World Championship and it was always ready with a creative way to optimise its position. Having AlphaZero next to us felt like having a human chess genius on tap, who never got tired and never asked for coffee. But an engine’s solution may look ugly to human eyes, even if it is unquestionably a winning move. A chess program or an “engine” like Stockfish searches through about 60 million positions a second. Back then, chess grandmasters were hired in to evaluate a series of typical positions and describe the considerations that led to the assessment, and then programmers turned these considerations into ever more sophisticated heuristics. But strangely enough, despite being programmed by humans, traditional chess engines don’t play quite like humans.ĭespite the hand-crafted heuristics, the fundament of an engine’s superiority lies in calculation: sifting through vast numbers of moves to find concrete ways to solve a position. We have taken some comfort from the fact that we taught these machines how to play. Since 1997, when IBM’s Deep Blue beat world champion and chess legend Garry Kasparov in a six-game match, chess players have accepted that machines are stronger at chess.
0 kommentar(er)
