Structure of Optimal Policies in Complex Queuing Systems.
S. Christian AlbrightPublished in: Oper. Res. (1977)
Keyphrases
- optimal policy
- markov decision processes
- queuing systems
- decision problems
- dynamic programming
- state space
- infinite horizon
- reinforcement learning
- average reward
- finite state
- long run
- multistage
- sufficient conditions
- markov decision process
- dynamic programming algorithms
- finite horizon
- control policies
- machine learning
- state dependent
- np hard