A state-space solution to the two-player decentralized optimal control problem.
Laurent LessardSanjay LallPublished in: Allerton (2011)
Keyphrases
- optimal control
- state space
- optimal control problems
- dynamic programming
- reinforcement learning
- control problems
- feedback control
- infinite horizon
- class of nonlinear systems
- hamilton jacobi bellman
- reinforcement learning algorithms
- multi agent
- risk sensitive
- control strategy
- markov decision processes
- lyapunov function
- optimal policy
- control law
- state variables
- mathematical model
- sufficient conditions
- particle swarm optimization
- optimal solution
- integer programming
- decision problems
- dynamical systems
- objective function
- machine learning