Keyphrases
- policy iteration
- markov decision processes
- model free
- reinforcement learning
- fixed point
- sample path
- least squares
- optimal policy
- markov decision process
- temporal difference
- finite state
- infinite horizon
- policy evaluation
- optimal control
- average reward
- linear programming
- supervised learning
- convergence rate
- markov decision problems
- dynamic programming
- random variables
- average cost