ML_optimiazation

Some tips regarding the optimization problem based on the ML apprach

References

The general idea to find the good combination

https://datascience.stackexchange.com/questions/53550/what-should-i-study-to-find-optimal-value-of-best-feature-combinations-in-machin

Different between the RL and the genetic algorithm. This is a really good explanation, the core thing is that if there are interaction in a time sequenced way for teh RL approach.

https://medium.com/xrpractices/reinforcement-learning-vs-genetic-algorithm-ai-for-simulations-f1f484969c56

Some examples about the flow fluid and the RL things

https://iopscience.iop.org/article/10.1088/1748-3190/aa6311/pdf?casa_token=DV-zABFF0jQAAAAA:I-iOvfpXfCBJibGMCO21rBGpvPJ-mqB891LYDE39_a4V-MLQU4J_kMdqPp3prV6_YiUiXWJezedUtqZkpkiyO05Uf2E

This one has a good figure to show different categories of the ML approach and their typical use case scenarios.
Machine Learning for Fluid Mechanics
Steven L. Brunton,1 Bernd R. Noack,2,3 and Petros Koumoutsakos4

Linear and non-linear optimization

https://eng.libretexts.org/Bookshelves/Industrial_and_Systems_Engineering/Chemical_Process_Dynamics_and_Controls_(Woolf)/08%3A_Optimization

Figure out optimization problem, control problem and optimization control problem

https://www.quora.com/What-is-the-difference-between-control-and-optimization

https://en.wikipedia.org/wiki/Optimal_control

difference between deep learning, optimization control, reinforcement learning, it is a good blog. it first distinguish between the dl vs optimal control and RL, and then it distinguish betweem the RL and optimization control

https://towardsdatascience.com/deep-learning-reinforcement-learning-optimal-control-what-a-mess-507dff27a603

Try to distinguish it is linear or non-linear optimization problem

reinforcement learning is used for non-linear control problem

Least square optimization

SGD

gradient descent and stocastic gradient descent.