AlphaGo
A Go-playing AI program developed by Google DeepMind.
1 article
Last mentioned AlphaGo is a Go-playing AI program developed by Google DeepMind. It chooses moves by combining deep neural networks with Monte Carlo tree search, and it became widely known after defeating Lee Sedol in 2016.
Its successor, AlphaZero, learned Go, chess and shogi through self-play without human game records. The two systems are among the best-known examples of AI research that combines reinforcement learning with search.
This entry is based on AIPOST articles and widely known facts. If something is wrong, please send us a correction request.