Koopman-based Policy Iteration for Robust Optimal Control.
Alexander KrolickiSarang SutavaniUmesh VaidyaPublished in: CoRR (2022)
Keyphrases
- optimal control
- policy iteration
- control problems
- infinite horizon
- dynamic programming
- markov decision processes
- reinforcement learning
- average cost
- control strategy
- approximate dynamic programming
- actor critic
- model free
- policy evaluation
- optimal control problems
- optimal policy
- fixed point
- least squares
- temporal difference
- state space
- average reward
- policy iteration algorithm
- markov decision problems
- markov decision process
- finite state
- linear programming
- control system