Temporal Difference Learning is an important class of incremental learning procedures which learn to predict outcomes of sequential processes through experience. Although these algorithms have been used in a variety of notorious intelligent systems such as Samuel's checker-player and Tesauro's Backgammon program, their convergence properties remain poorly understood. This paper provides a brief summary of the theoretical basis for these algorithms and documents observed convergence performance in a variety of experiments. The implications of these results are also briefly discussed.
Convergence behavior of temporal difference learning
1996-01-01
498793 byte
Conference paper
Electronic Resource
English
Covergence Behavior of Temporal Difference Learning
British Library Conference Proceedings | 1996
|Intersection traffic control optimization method based on temporal difference learning
European Patent Office | 2021
|