The lagging anchor algorithm: Reinforcement learning in two-player zero-sum games with imperfect information

Machine Learning

Volumn 49, Issue 1, 2002, Pages 5-37

  Dahl, Fredrik A ^a  

^a NORWEGIAN DEFENCE RESEARCH ESTABLISHMENT FFI   (Norway)

Author keywords

Imperfect information; Neural net; Reinforcement learning; Two player zero sum game

Indexed keywords

COMPUTATIONAL COMPLEXITY; CONVERGENCE OF NUMERICAL METHODS; GAME THEORY; LEARNING ALGORITHMS; NEURAL NETWORKS;

IMPERFECT INFORMATION; REINFORCEMENT LEARNING; TWO PLAYER ZERO SUM GAME;

LEARNING SYSTEMS;

EID: 0036778915     PISSN: 08856125     EISSN: None     Source Type: Journal    
DOI: 10.1023/A:1014063505958     Document Type: Article

References (33)

1. Experimental studies of neural net training and human learning in a military air campaign game
2. The tactical air game: A multimove game with mixed strategy solution
3. Adaptation in games-2 solutions to the Crawford puzzle
4. Adaptive tactics in games-Further solutions to the Crawford puzzle
5. Learning the optimal strategy in a zero-sum game
6. Three games designed for the study of human and automated decision making
7. Minimax TD-learning with neural nets in a Markov game
8. Predicting how people play games: Reinforcement learning in experimental games with unique, mixed strategy equilibria
9. On classification of games and evaluation of players-with some sweeping generalizations about the literature
10. Reinforcement learning applied to a differential game
11. Efficient solutions of extensive two-person games
12. Markov games as a framework for multi-agent reinforcement learning
13. Game-playing and game-learning automata
14. Some studies in machine learning using the game of checkers
15. Learning to play strong poker
16. Anticipatory learning in two-person games
17. Learning to predict by the methods of temporal differences
18. A unified analysis of value-function-based reinforcement-learning algorithms
19. Practical issues in temporal difference learning
20. A parallel network that learns to play backgammon
21. Learning from delayed rewards