Keyphrases
- policy iteration
- markov decision processes
- fixed point
- model free
- reinforcement learning
- optimal policy
- least squares
- sample path
- policy evaluation
- markov decision process
- finite state
- infinite horizon
- temporal difference
- convergence rate
- optimal control
- linear programming
- average reward
- function approximation
- state space
- linear program
- markov decision problems
- dynamic programming
- optical flow