Input Generalization in Delayed Reinforcement Learning: An Algorithm and Performance Comparisons.
David ChapmanLeslie Pack KaelblingPublished in: IJCAI (1991)
Keyphrases
- reinforcement learning
- times faster
- learning algorithm
- preprocessing
- improved algorithm
- dynamic programming
- input data
- monte carlo
- detection algorithm
- stochastic approximation
- computational complexity
- path planning
- cost function
- theoretical analysis
- computational cost
- model free
- linear programming
- high accuracy
- data sets
- k means
- search space
- genetic algorithm
- expectation maximization
- optimization algorithm
- np hard
- multi agent
- similarity measure
- machine learning