Markov Decision Process and Approximate Dynamic Programming for a Patient Assignment Scheduling problem.
Malgorzata M. O'ReillySebastian KrasnickiJames MontgomeryMojtaba HeydarRichard TurnerPieter Van DamPeter MareePublished in: CoRR (2024)
Keyphrases
- approximate dynamic programming
- markov decision process
- scheduling problem
- policy iteration
- reinforcement learning
- average cost
- markov decision processes
- state space
- optimal policy
- dynamic programming
- np hard
- linear program
- finite horizon
- infinite horizon
- factored mdps
- linear programming
- initial state
- state action
- long run
- markov decision problems
- finite state
- finite number
- function approximation
- reward function
- optimal control
- step size
- control policy
- reinforcement learning algorithms
- partially observable
- model free
- action space
- dynamical systems
- generative model
- search space
- search algorithm