Online policy iteration based algorithms to solve the continuous-time infinite horizon optimal control problem.
Kyriakos G. VamvoudakisDraguna L. VrabieFrank L. LewisPublished in: ADPRL (2009)
Keyphrases
- optimal control
- infinite horizon
- policy iteration
- control problems
- finite horizon
- dynamic programming
- markov decision processes
- optimal control problems
- markov decision problems
- single item
- control strategy
- markov decision process
- reinforcement learning
- optimal policy
- average cost
- partially observable
- model free
- production planning
- average reward
- policy evaluation
- stochastic demand
- fixed point
- least squares
- policy iteration algorithm
- long run
- holding cost
- temporal difference
- lost sales
- state space