Practical Issues in Temporal Difference Learning

Tesauro, Gerald

Dec-31-1992–Neural Information Processing Systems

TO('\) is an algorithm for adjusting the weights in a connectionist network which 259 260 Tesauro has the following form:

artificial intelligence, machine learning, reinforcement learning, (17 more...)

Neural Information Processing Systems

Dec-31-1992

Conferences PDF

Country:
- Europe > Netherlands > North Holland > Amsterdam (0.04)

Industry:
- Leisure & Entertainment > Games > Backgammon (0.49)

Technology:
- Information Technology > Artificial Intelligence > Machine Learning > Reinforcement Learning (1.00)