TD-Gammon, a Self-Teaching Backgammon Program, Achieves Master-Level Play.
Gerald TesauroPublished in: Neural Comput. (1994)
Keyphrases
- temporal difference learning
- learning process
- game playing
- learning environment
- higher level
- learning algorithm
- evaluation function
- programming course
- temporal difference
- reinforcement learning
- online learning
- learning systems
- higher education
- practical experience
- novice programmers
- elementary school
- computer programs
- problem based learning
- hong kong
- lower level
- fixed point