Keyphrases
- policy iteration
- markov decision processes
- optimal policy
- model free
- reinforcement learning
- fixed point
- sample path
- factored mdps
- decision diagrams
- policy evaluation
- least squares
- finite state
- infinite horizon
- approximate dynamic programming
- markov decision process
- average reward
- markov decision problems
- state space
- transition matrices
- dynamic programming
- average cost
- optimal control
- dynamical systems
- optical flow
- markov games
- finite horizon
- long run
- discounted reward
- decision processes
- reward function
- cost function
- state and action spaces
- machine learning