Keyphrases
- policy iteration
- lower bound
- markov decision processes
- model free
- average case complexity
- upper bound
- fixed point
- least squares
- optimal policy
- reinforcement learning
- sample path
- finite state
- markov decision process
- policy evaluation
- temporal difference
- infinite horizon
- average reward
- objective function
- linear programming
- np hard
- markov decision problems
- worst case
- state space
- dynamic programming
- optimal control
- machine learning
- average cost
- convergence rate
- optimal solution
- linear program
- sufficient conditions
- support vector
- discounted reward
- neural network