Regret Lower Bound and Optimal Algorithm in Finite Stochastic Partial Monitoring.
Junpei KomiyamaJunya HondaHiroshi NakagawaPublished in: CoRR (2015)
Keyphrases
- worst case
- lower bound
- optimal solution
- dynamic programming
- competitive ratio
- np hard
- objective function
- upper bound
- learning algorithm
- detection algorithm
- monte carlo
- cost function
- regret bounds
- preprocessing
- constant factor
- computational complexity
- locally optimal
- average case
- exhaustive search
- lower and upper bounds
- confidence bounds
- globally optimal
- branch and bound
- segmentation algorithm
- least squares
- state space
- search space
- optimal cost
- k means