Combined Fixed Point and Policy Iteration for Hamilton-Jacobi-Bellman Equations in Finance.
Y. HuangPeter A. ForsythGeorge LabahnPublished in: SIAM J. Numer. Anal. (2012)
Keyphrases
- fixed point
- policy iteration
- hamilton jacobi bellman
- approximate dynamic programming
- optimal control
- bellman residual
- dynamical systems
- sample path
- control problems
- policy evaluation
- average reward
- nonlinear systems
- sufficient conditions
- temporal difference learning
- markov decision processes
- differential equations
- belief propagation
- reinforcement learning
- mathematical model
- least squares