Policy iteration for Hamilton-Jacobi-Bellman equations with control constraints.
Sudeep KunduKarl KunischPublished in: Comput. Optim. Appl. (2024)
Keyphrases
- hamilton jacobi bellman
- optimal control
- policy iteration
- control problems
- reinforcement learning
- approximate dynamic programming
- stochastic control
- markov decision processes
- infinite horizon
- dynamic programming
- fixed point
- control strategy
- model free
- temporal difference
- optimal policy
- state space
- markov decision process
- adaptive control
- control system
- queueing systems
- least squares
- average reward
- hamilton jacobi
- constrained optimization
- average cost
- nonlinear systems
- machine learning
- differential equations
- dynamical systems
- model checking
- mathematical model
- learning algorithm