On generalized policy iteration for continuous-time linear systems.
Jae Young LeeTae Yoon ChunJin Bae ParkYoon Ho ChoiPublished in: CDC/ECC (2011)
Keyphrases
- linear systems
- policy iteration
- dynamical systems
- fixed point
- markov decision processes
- optimal control
- sufficient conditions
- state space
- reinforcement learning
- model free
- optimal policy
- finite state
- sample path
- least squares
- markov decision process
- coefficient matrix
- temporal difference
- policy evaluation
- markov chain
- infinite horizon
- average reward
- markov decision problems
- global optimization
- sparse linear systems
- linear program
- function approximation
- convergence rate
- linear programming
- graphical models
- evolutionary algorithm