Every story and comment from the Hacker News API, in a layout borrowed from 2001.
A comment on AlphaGo beats Lee Sedol again in match 2 of 5. Parent comment
It uses MCTS, which is unlike minimax. It doesn't use temporal difference learning, although they say that the policy somewhat resembles TD.
That doesn't sound like 'essentially built on', its sounds maybe like 'slightly influenced by'
Tesauro's work on TD-Gammon was pioneering at the high level, i.e. combining reinforcement learning + self-play + neural networks.
It uses MCTS, which is unlike minimax. It doesn't use temporal difference learning, although they say that the policy somewhat resembles TD.
That doesn't sound like 'essentially built on', its sounds maybe like 'slightly influenced by'