Machine learning control

Uses your system voice; voice and rate in settings.

Snapshot

≈ 2 min read

Names in other languages

No names in other languages are held for this entry yet.

Article bodies are English and are not machine-translated. A name in another language is not a translation of the article.

Machine learning control (MLC) is a subfield of machine learning, intelligent control, and control theory which aims to solve optimal control problems with machine learning methods. Key applications are complex nonlinear systems for which linear control theory methods are not applicable.

How it works

Machine learning control (MLC) is a subfield of machine learning, intelligent control, and control theory which aims to solve optimal control problems with machine learning methods. Key applications are complex nonlinear systems for which linear control theory methods are not applicable. Adaptive Dynamic Programming (ADP), also known as approximate dynamic programming or neuro-dynamic programming, is a machine learning control method that combines reinforcement learning with dynamic programming to solve optimal control problems for complex systems.

ADP addresses the "curse of dimensionality" in traditional dynamic programming by approximating value functions or control policies using parametric structures such as neural networks. The core idea revolves around learning a control policy that minimizes a long-term cost function J , defined as J(x(t)) = \int_{t}^{\infty} e^{-\gamma(\tau-t)} r(x(\tau), u(\tau)) \, d\tau , where x is the system state, u is the control input, r is the instantaneous reward, and \gamma is a discount factor.

Criticism and limits

ADP employs two interacting components: a critic that estimates the value function V(x) \approx J(x) , and an actor that updates the control policy u(x) . The critic and actor are trained iteratively using temporal difference learning or gradient descent to satisfy the Hamilton-Jacobi-Bellman (HJB) equation: \min_{u} \left( r(x,u) + \frac{\partial V}{\partial x} f(x,u) \right) = 0, where f(x,u) describes the system dynamics.

Evidence and sources

Key variants include heuristic dynamic programming (HDP), dual heuristic programming (DHP), and globalized dual heuristic programming (GDHP). ADP has been applied to robotics, power systems, and autonomous vehicles, offering a data-driven framework for near-optimal control without requiring full system models. Challenges remain in ensuring stability guarantees and convergence for general nonlinear systems.

Text derived from https://en.wikipedia.org/w/index.php?oldid=1375385472 under CC BY-SA 4.0; modifications have been made.

Sources cited in this revision

11 named source(s) extracted from the cited revision. A source with no author is shown by its publication; nothing is invented.