Experience generalization for concurrent reinforcement learners: the minimax-QS algorithm.
Carlos H. C. RibeiroRenê PegoraroAnna Helena Reali CostaPublished in: AAMAS (2002)
Keyphrases
- worst case
- cost function
- learning algorithm
- times faster
- experimental evaluation
- dynamic programming
- improved algorithm
- theoretical analysis
- optimal solution
- np hard
- path planning
- e learning
- k means
- objective function
- clustering method
- detection algorithm
- computational cost
- probabilistic model
- convergence rate
- optimization algorithm
- preprocessing
- particle swarm optimization
- expectation maximization
- matching algorithm
- decision trees
- collaborative learning
- high accuracy
- machine learning
- similarity measure
- multi objective
- learning process
- search space
- association rules
- learning environment