Approximate dynamic programming using Bellman residual elimination and Gaussian process regression.
Brett BethkeJonathan P. HowPublished in: ACC (2009)
Keyphrases
- approximate dynamic programming
- gaussian process regression
- policy iteration
- markov decision processes
- reinforcement learning
- model free
- optimal policy
- fixed point
- gaussian processes
- temporal difference
- least squares
- linear program
- finite state
- gaussian process
- dynamic programming
- markov decision process
- infinite horizon
- step size
- convergence rate
- state space
- linear programming
- markov decision problems
- optimal control
- average cost
- multistage
- markov random field