![Computational neuroscience / Backgammon / Neurogammon / TD-Gammon / Temporal difference learning / Monte Carlo method / Reinforcement learning / Neural network / Stochastic / Machine learning / Games / Mathematics Computational neuroscience / Backgammon / Neurogammon / TD-Gammon / Temporal difference learning / Monte Carlo method / Reinforcement learning / Neural network / Stochastic / Machine learning / Games / Mathematics](https://www.pdfsearch.io/img/fc16fbaa3b9b07f4b533a77bc40f7fa4.jpg)
| Document Date: 1997-09-18 21:19:22 Open Document File Size: 28,37 KBShare Result on Facebook
Company IBM / Learning & Vision Group Artificial Intelligence Laboratory / Neural Information Processing Systems / MIT Press / / IndustryTerm manufacturing process control / tree-search based techniques / stochastic systems / on-line and off-line methods / control systems / / Organization MIT / / Person Gerald Tesauro / Monte-Carlo / Gregory Galperin / Paul Viola / / Position VP / Base player / maxa VP / base controller / bad intermediate player / computer backgammon player / player / / Product Monte-Carlo / / PublishedMedium Machine Learning / / Technology Machine Learning / simulation / neural network / artificial intelligence / process control / /
SocialTag |