Greatest Fixed Points of Probabilistic Min/Max Polynomial Equations, and Reachability for Branching Markov Decision Processes.
Kousha EtessamiAlistair StewartMihalis YannakakisPublished in: CoRR (2015)
Keyphrases
- min max
- fixed point
- markov decision processes
- policy iteration
- polynomial equations
- stationary points
- state space
- dynamical systems
- finite state
- sufficient conditions
- optimal policy
- reinforcement learning
- dynamic programming
- average cost
- decision theoretic planning
- partially observable
- bayesian networks
- generative model
- infinite horizon
- probabilistic model
- action space
- objective function
- belief propagation
- reinforcement learning algorithms
- posterior probability
- least squares
- markov decision process
- search space
- supervised learning