Semidefinite relaxations for stochastic optimal control policies.
Matanya B. HorowitzJoel W. BurdickPublished in: ACC (2014)
Keyphrases
- control policies
- semidefinite
- control policy
- semidefinite programming
- optimal policy
- reinforcement learning
- control system
- finite horizon
- convex relaxation
- control strategies
- motion control
- interior point methods
- sufficient conditions
- higher dimensional
- action space
- lower bound
- convex sets
- optimization problems
- state space
- mobile robot
- objective function