Reward Model Solution Methods with Impulse and Rate Rewards: An Algorithm and Numerical Results.
Muhammad A. QureshiWilliam H. SandersPublished in: Perform. Evaluation (1994)
Keyphrases
- mathematical model
- preprocessing
- objective function
- theoretical analysis
- computational cost
- significant improvement
- probabilistic model
- numerical algorithms
- model free
- qualitative and quantitative
- optimal solution
- input data
- optimization method
- learned models
- cost function
- recognition algorithm
- theoretical guarantees
- control policy
- tree structure
- detection algorithm
- learning algorithm
- dynamic programming
- parameter estimation
- gradient method
- similarity measure
- reinforcement learning
- sensitivity analysis
- numerical methods
- np hard
- search space
- optimization algorithm
- closed form
- classification algorithm
- em algorithm
- linear regression
- bayesian framework
- k means
- reconstruction method
- expectation maximization
- iterative algorithms
- average reward
- genetic algorithm