Convergence of the Value Functions of Discounted Infinite Horizon Optimal Control Problems with Low Discount Rates.
Fabian WirthPublished in: Math. Oper. Res. (1993)
Keyphrases
- infinite horizon
- optimal control
- optimal control problems
- production planning
- finite horizon
- dynamic programming
- single item
- control strategy
- stochastic demand
- average cost
- optimal policy
- markov decision process
- long run
- reinforcement learning
- policy iteration
- markov decision processes
- convergence rate
- machine learning
- control law
- convergence speed
- mathematical model
- lower bound