Mean field for Markov Decision Processes: from Discrete to Continuous Optimization
Nicolas GastBruno GaujalJean-Yves Le BoudecPublished in: CoRR (2010)
Keyphrases
- continuous optimization
- markov decision processes
- optimization methods
- optimal policy
- reinforcement learning
- simulated annealing
- finite state
- state space
- dynamic programming
- policy iteration
- linear models
- transition matrices
- decision theoretic planning
- optimization strategy
- belief networks
- model based reinforcement learning
- metaheuristic
- average cost
- markov decision process
- em algorithm
- infinite horizon
- neural network
- action sets
- bayesian networks
- action space
- markov random field
- partially observable
- objective function
- machine learning
- markov networks
- optimization method