Keyphrases
- factored mdps
- policy iteration
- markov decision processes
- fixed point
- model free
- reinforcement learning
- optimal policy
- approximate dynamic programming
- least squares
- finite state
- infinite horizon
- temporal difference
- markov decision problems
- linear programming
- markov decision process
- optimal control
- state space
- convergence rate
- reinforcement learning algorithms
- context specific
- probabilistic model
- dynamic programming
- partially observable
- decision processes
- learning algorithm