Energy Optimization of Wind Turbines via a Neural Control Policy Based on Reinforcement Learning Markov Chain Monte Carlo Algorithm.
Vahid Tavakol AghaeiArda AgababaogluPeiman NaseradinmousaviSinan YildirimSerhat YesilyurtAhmet OnatPublished in: CoRR (2022)
Keyphrases
- control policy
- markov chain monte carlo
- reinforcement learning
- learning algorithm
- dynamic programming
- long run
- search space
- generative model
- bayesian inference
- probabilistic model
- machine learning
- posterior probability
- monte carlo
- energy function
- least squares
- optimal solution
- neural network
- expectation maximization
- particle filter
- bayesian framework
- k means
- feature selection