 | NASA Study Group on Machine Intelligence and Robotics - 1980 - Страниц: 284
...something at each move." D. The Basic Credit-assignment Problem for Complex Reinforcement Learning Systems In playing a complex game such as chess or checkers,...for the success among the multitude of decisions? As Newell noted, It is extremely doubtful whether there is enough information in "win, lose, or draw"... | |
 | Ronald Chrisley, Sander Begeer - 2000 - Страниц: 608
...something at each move.19 D The basic credit-assignment problem for complex reinforcement learning systems In playing a complex game such as chess or checkers,...for the success among the multitude of decisions? As Newell noted. It is extremely doubtful whether there is enough information in "win, lose, or draw"... | |
| |
The Basic Credit-assignment Problem for Complex Reinforcement Learning Systems In playing a complex game such as chess or checkers, or in writing a computer program, one has a definite success criterion — the game is won or lost. But in the course of... 