Optimal Policies for n-Dimensional Singular Stochastic Control Problems Part I: The Skorokhod Problem.
Lukasz KrukPublished in: SIAM J. Control. Optim. (2000)
Keyphrases
- control problems
- optimal policy
- stochastic control
- reinforcement learning
- optimal control
- markov decision processes
- infinite horizon
- decision problems
- queueing systems
- dynamic programming
- control policies
- state dependent
- finite horizon
- state space
- long run
- average cost
- finite state
- multistage
- policy iteration
- average reward
- function approximation
- average reward reinforcement learning
- reinforcement learning algorithms
- partially observable
- adaptive control
- machine learning
- brownian motion
- dynamic programming algorithms
- learning algorithm
- markov decision process
- asymptotically optimal
- model free
- continuous state spaces
- serial inventory systems
- inventory level
- lost sales
- initial state
- partially observable markov decision processes
- markov decision problems
- sufficient conditions
- control system