Temporal Difference Learning and TD-Gammon

@article{Tesauro1995TemporalDL,
  title={Temporal Difference Learning and TD-Gammon},
  author={G. Tesauro},
  journal={J. Int. Comput. Games Assoc.},
  year={1995},
  volume={18},
  pages={88}
}
  • G. Tesauro
  • Published 1995
  • Computer Science
  • J. Int. Comput. Games Assoc.
We provide an abstract, selectively u§ing the author's formulations: "The article presents a game-learning program called TD-GAMMON. TD-GAMMON is a neural network that trains itself to be an evaluation function for the game of backgammon by playing against itself and learning from the outcome. It was not developed to surpass all previous computer programs in backgammon; rather, its purpose was to explore some new ideas and approaches to traditional problems in reinforcement learning. 
655 Citations
Why did TD-Gammon Work?
  • 33
  • PDF
Comparing Training Paradigms for Learning to Play Backgammon
  • PDF
Supervised reinforcement learning in discrete environment domains
  • 1
  • PDF
CHECKERS : TD ( λ ) LEARNING APPLIED FOR DETERMINISTIC GAME
The Significance of Temporal-Difference Learning in Self-Play Training TD-Rummy versus EVO-rummy
  • 14
  • PDF
Performance analysis of a new updating rule for TD(/spl lambda/) learning in feedforward networks for position evaluation in Go game
  • 9
  • PDF
Reinforcement learning in board games
  • 63
  • PDF
Adapting Reinforcement Learning to Tetris
  • 6
  • Highly Influenced
  • PDF
The History of Computer Games
  • 10
  • PDF
Evolving a Neural Network Location Evaluator to Play Ms. Pac-Man
  • 125
  • PDF
...
1
2
3
4
5
...