#controlengineering — Public Fediverse posts

"Liquid" #neuralnetworks can keep on #machinelearning while embedded in drones to account for unexpected environment, events or noise and improve the commands: https://robohub.org/drones-navigate-unseen-environments-with-liquid-neural-networks/

It reminds me of a fantasy I had when I was a student in #controlengineering: we could design an PID to tune itself to look for better responses and change parameters in face of instabilities.

Dynamic Programming is one way to arrive at the solution of the Markov Decision Process or MDP used in Reinforcement Learning (RL) problems.

In the third article on the Foundational RL series, I discuss dynamic programming and briefly talk about Approximate Dynamic Programming.

https://towardsdatascience.com/foundational-rl-dynamic-programming-28f96f6fb40e

#controlsystems #controltheory #controlengineering #engineering #learning #rl #reinforcementlearning #datascience #machinelearning #ml #ai #autonomousdriving #robotics #dynamicprogramming

Dynamic Programming is one way to arrive at the solution of the Markov Decision Process or MDP used in Reinforcement Learning (RL) problems.

In the third article on the Foundational RL series, I discuss dynamic programming and briefly talk about Approximate Dynamic Programming.

https://towardsdatascience.com/foundational-rl-dynamic-programming-28f96f6fb40e

#controlsystems #controltheory #controlengineering #engineering #learning #rl #reinforcementlearning #datascience #machinelearning #ml #ai #autonomousdriving #robotics #dynamicprogramming

If you are looking to get started with Reinforcement Learning (RL), do check out these two articles:

1. https://towardsdatascience.com/foundational-rl-markov-states-markov-chain-and-markov-decision-process-be8ccc341005

2. https://towardsdatascience.com/foundational-rl-solving-markov-decision-process-d90b7e134c0b

I explain the concept of RL using an example from autonomous driving control.

#reinforcementlearning #learning #machinelearning #datascience #controlsystems #controlengineering #autonomousdriving #autonomousvehicles #ml #ai #python

Did you know that Bellman Equation is also called the Hamilton-Jacobi equation in control theory or control engineering?

Check out my recent article on Bellman Equation for Reinforcement Learning in the context of the Markov Decision Process.

https://towardsdatascience.com/foundational-rl-solving-markov-decision-process-d90b7e134c0b

#controlsystems #controltheory #controlengineering #engineering #learning #rl #reinforcementlearning #datascience #machinelearning #ml #ai #artificialintelligence #python #autonomousdriving #autonomousvehicles #robotics