Economic MPC of Markov Decision Processes: Dissipativity in undiscounted infinite-horizon optimal control.
Sebastien GrosMario ZanonPublished in: Autom. (2022)
Keyphrases
- infinite horizon
- optimal control
- markov decision processes
- dynamic programming
- policy iteration
- reinforcement learning
- finite horizon
- control problems
- average cost
- stochastic demand
- risk sensitive
- state space
- optimal policy
- partially observable
- finite state
- production planning
- control strategy
- markov decision process
- stochastic games
- single item
- action space
- average reward
- reinforcement learning algorithms
- linear programming
- planning under uncertainty
- markov decision problems
- actor critic
- dec pomdps
- decision processes
- function approximation
- decision making
- policy iteration algorithm