Continuity of the Value Function in Sparse Optimal Control.
Takuya IkedaMasaaki NagaharaPublished in: CoRR (2014)
Keyphrases
- optimal control
- dynamic programming
- control problems
- feedback control
- policy gradient
- class of nonlinear systems
- risk sensitive
- control strategy
- control law
- reinforcement learning
- infinite horizon
- optimal control problems
- brownian motion
- policy iteration
- piecewise constant
- particle swarm optimization
- stochastic control
- machine learning