An Accelerated Value/Policy Iteration Scheme for Optimal Control Problems and Games.
Alessandro AllaMaurizio FalconeDante KalisePublished in: ENUMATH (2013)
Keyphrases
- policy iteration
- optimal control
- optimal control problems
- markov decision processes
- infinite horizon
- model free
- fixed point
- reinforcement learning
- optimal policy
- linear programming
- least squares
- dynamic programming
- finite state
- temporal difference
- machine learning
- artificial neural networks
- average cost
- optimal solution
- control theory