Proving Termination by Policy Iteration.
Damien MasséPublished in: Electron. Notes Theor. Comput. Sci. (2012)
Keyphrases
- policy iteration
- term rewrite systems
- markov decision processes
- model free
- reinforcement learning
- optimal policy
- fixed point
- least squares
- sample path
- markov decision process
- policy evaluation
- convergence rate
- infinite horizon
- temporal difference
- markov decision problems
- average reward
- state space
- finite state
- linear programming
- optimal control
- function approximation
- discounted reward
- average cost
- dynamic programming
- neural network