Programming backgammon using self-teaching neural nets

TD-Gammon is a neural network that is able to teach itself to play backgammon solely by playing against itself and learning from the results. Starting from random initial play, TD-Gammon's self-teaching methodology results in a surprisingly strong program: without lookahead, its positional judg...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:Artificial intelligence Ročník 134; číslo 1; s. 181 - 199
Hlavní autor: Tesauro, Gerald
Médium: Journal Article
Jazyk:angličtina
Vydáno: Elsevier B.V 2002
Témata:
Artificial intelligence
Backgammon
Doubling strategy
Games
Neural networks
Reinforcement learning
Rollouts
Temporal difference learning
Temporal difference learning
Neural networks
Reinforcement learning
Games
Rollouts
Backgammon
Doubling strategy
ISSN:0004-3702, 1872-7921
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí:TD-Gammon is a neural network that is able to teach itself to play backgammon solely by playing against itself and learning from the results. Starting from random initial play, TD-Gammon's self-teaching methodology results in a surprisingly strong program: without lookahead, its positional judgement rivals that of human experts, and when combined with shallow lookahead, it reaches a level of play that surpasses even the best human players. The success of TD-Gammon has also been replicated by several other programmers; at least two other neural net programs also appear to be capable of superhuman play. Previous papers on TD-Gammon have focused on developing a scientific understanding of its reinforcement learning methodology. This paper views machine learning as a tool in a programmer's toolkit, and considers how it can be combined with other programming techniques to achieve and surpass world-class backgammon play. Particular emphasis is placed on programming shallow-depth search algorithms, and on TD-Gammon's doubling algorithm, which is described in print here for the first time.
Bibliografie:ObjectType-Article-2
SourceType-Scholarly Journals-1
ObjectType-Feature-1
content type line 23
ObjectType-Article-1
ObjectType-Feature-2
ISSN:0004-3702
1872-7921
DOI:10.1016/S0004-3702(01)00110-2