Program Analysis with Local Policy Iteration.
Egor George KarpenkovDavid MonniauxPhilipp WendlerPublished in: VMCAI (2016)
Keyphrases
- policy iteration
- markov decision processes
- optimal policy
- fixed point
- reinforcement learning
- model free
- sample path
- least squares
- finite state
- policy evaluation
- temporal difference
- average reward
- markov decision process
- infinite horizon
- optimal control
- convergence rate
- state space
- markov decision problems
- dynamic programming
- linear programming
- image segmentation
- graphical models
- supply chain
- artificial neural networks
- discounted reward