Optimal Policies for Data Base Reorganization.
Haim MendelsonUri YechialiPublished in: Oper. Res. (1981)
Keyphrases
- optimal policy
- database
- decision problems
- markov decision processes
- reinforcement learning
- state space
- multistage
- long run
- finite horizon
- infinite horizon
- finite state
- dynamic programming
- average cost
- initial state
- sufficient conditions
- state dependent
- serial inventory systems
- bayesian reinforcement learning
- dynamic programming algorithms
- average reward
- policy iteration
- markov decision process
- average reward reinforcement learning
- inventory level
- lost sales
- markov decision problems
- partially observable markov decision processes
- linear programming
- control policies