Mean Field for Markov Decision Processes: From Discrete to Continuous Optimization.
Nicolas GastBruno GaujalJean-Yves Le BoudecPublished in: IEEE Trans. Autom. Control. (2012)
Keyphrases
- continuous optimization
- markov decision processes
- optimization methods
- finite state
- simulated annealing
- reinforcement learning
- dynamic programming
- transition matrices
- optimal policy
- markov random field
- state space
- average cost
- linear models
- metaheuristic
- decision theoretic planning
- policy iteration
- optimization strategy
- infinite horizon
- action sets
- average reward
- belief networks
- model based reinforcement learning
- partially observable
- action space
- machine learning
- probabilistic model
- bayesian inference
- markov decision process
- neural network