Greatest Fixed Points of Probabilistic Min/Max Polynomial Equations, and Reachability for Branching Markov Decision Processes.
Kousha EtessamiAlistair StewartMihalis YannakakisPublished in: ICALP (2) (2015)
Keyphrases
- min max
- fixed point
- markov decision processes
- polynomial equations
- policy iteration
- stationary points
- state space
- dynamical systems
- finite state
- optimal policy
- sufficient conditions
- reinforcement learning
- decision theoretic planning
- infinite horizon
- bayesian networks
- probabilistic model
- generative model
- dynamic programming
- variational inequalities
- action space
- reinforcement learning algorithms
- belief propagation
- average cost
- markov decision process
- partially observable
- graphical models
- nonlinear programming
- markov decision problems