Solving nonogram puzzles by reinforcement learning.
Frédéric DandurandDenis CousineauThomas R. ShultzPublished in: CogSci (2012)
Keyphrases
- reinforcement learning
- crossword puzzles
- jigsaw puzzle
- function approximation
- combinatorial optimization
- markov decision problems
- real time
- markov decision processes
- least squares
- multi agent
- machine learning
- state space
- knowledge representation
- temporal difference
- reinforcement learning algorithms
- control problems
- real robot
- temporal difference learning
- learning algorithm