Keyphrases
- policy iteration
- markov decision processes
- factored mdps
- model free
- optimal policy
- sample path
- decision diagrams
- reinforcement learning
- fixed point
- least squares
- markov decision process
- policy evaluation
- average reward
- finite state
- approximate dynamic programming
- temporal difference
- markov decision problems
- state space
- transition matrices
- dynamic programming
- infinite horizon
- discounted reward
- average cost
- reinforcement learning algorithms
- convergence rate
- approximate policy iteration
- decision processes
- optimal control
- markov games
- linear programming
- finite horizon
- learning tasks
- state and action spaces