A Policy Iteration Technique for Time Elapse over Template Polyhedra.
Sriram SankaranarayananThao DangFranjo IvancicPublished in: HSCC (2008)
Keyphrases
- policy iteration
- markov decision processes
- model free
- reinforcement learning
- fixed point
- least squares
- optimal policy
- sample path
- temporal difference
- infinite horizon
- finite state
- markov decision process
- policy evaluation
- optimal control
- state space
- convergence rate
- average reward
- special case
- markov decision problems
- evaluation function
- input image
- average cost