Google Develops An AI That Can Learn Both Chess And Pac-Man
Google Develops An AI That Can Learn Both Chess And Pac-Man
Google Develops An AI That Can Learn Both Chess And Pac-Man
By John Timmer
December 24, 2020
Summary
An algorithm could always have perfect knowledge of the state of the game and know every possible move that both it and its opponent could make.
The new system, which DeepMind is calling MuZero, is based in part on DeepMind's work with the AlphaZero AI, which taught itself to master rule-based games like chess and Go. But MuZero also adds a new twist that makes it substantially more flexible.
Critically, the prediction it makes is based on its internal model of game states-not the actual visual representation of the game, such as the location of chess pieces.
Finally, the value of the move is evaluated using the algorithms predictions of any immediate rewards gained from that move and the final state of the game, such as the win or lose outcome of chess.
These can involve the same searches down trees of potential game states done by earlier chess algorithms, but in this case, the trees consist of the AI's own internal game models.
MuZero took just under a million games against its predecessor AlphaZero in order to reach a similar level of performance in chess or shogi.
While there are still some circumstances where it lags behind, it's now made model-based AI's competitive in these games, while maintaining its ability to handle rule-based games like chess and Go. Overall, this is an impressive achievement and an indication of how AIs are growing in sophistication.
Reference
Timmer, J. (2020, December 24). Google develops an AI that can learn both chess and Pac-Man. Retrieved January 06, 2021, from https://arstechnica.com/science/2020/12/google-develops-an-ai-that-can-learn-both-chess-and-pac-man/