Approximately Optimal Control of Nonlinear Dynamic Stochastic Problems with Learning: The OPTCON Algorithm.
Dmitri BlueschkeViktoria Blueschke-NikolaevaReinhard NeckPublished in: Algorithms (2021)
Keyphrases
- optimal control
- learning algorithm
- dynamic programming
- actor critic
- reinforcement learning
- control problems
- optimal control problems
- linear programming
- linear systems
- rl algorithms
- objective function
- np hard
- policy gradient
- particle swarm optimization
- model free
- nonlinear dynamics
- optimal solution
- stochastic control