Solving a decision problem with graded rewards.
José A. HerenciaMaría Teresa LamataPublished in: Int. J. Intell. Syst. (1999)
Keyphrases
- decision problems
- bandit problems
- sequential decision making
- influence diagrams
- np hard
- computational complexity
- decision model
- optimal policy
- discrete optimization problems
- optimal strategy
- decision processes
- utility function
- reinforcement learning
- markov decision processes
- combinatorial optimization
- bayesian decision problems
- partially observable markov decision processes
- pspace complete
- machine learning
- partially observable
- decision analysis
- expressive power
- state space