Optimal Policies for Sequential Bernoulli Experiments with Switching Costs.
Harald BenzingDieter KalinRadu TheodorescuPublished in: J. Inf. Process. Cybern. (1987)
Keyphrases
- optimal policy
- switching costs
- markov decision processes
- decision problems
- state space
- dynamic programming
- infinite horizon
- reinforcement learning
- multistage
- average reward
- finite horizon
- long run
- finite state
- prior studies
- state dependent
- dynamic programming algorithms
- markov decision process
- average reward reinforcement learning
- policy iteration
- individual level
- online services
- sufficient conditions
- serial inventory systems
- initial state
- network effects
- machine learning
- decision making