Reinforcement Learning and Intelligent Control

Specialist course: reinforcement learning methods for decision-making and control problems.

ASA-T19 24 horas En vivo en línea Avanzado

Lo que aprenderás

  • Formulate problems as Markov decision processes
  • Implement value- and policy-based methods
  • Apply RL to control tasks
  • Evaluate when RL is (and is not) appropriate

Specialist course: reinforcement learning methods for decision-making and control problems.

Duration: 4-5 days (proposed). Delivery: face-to-face at your premises or live online; available as a private corporate session.

Practical exercises

  • Train an agent in a simulated environment

Computing requirements: Specialist offering, not an initial flagship. Optional: rented cloud GPU for the larger exercises (one mid-range GPU, about 10-20 hours per participant, estimated at a few US dollars per hour). All core exercises run on CPU with small datasets.

Temario

  1. MDPs and dynamic programming · 5 h
  2. Value-based methods · 5 h
  3. Policy-gradient methods · 5 h
  4. Control applications · 5 h
  5. Practical limits · 4 h

Requisitos

  • Python, probability and ML basics

A quién va dirigido

  • Engineers and researchers

Software y equipo

  • Laptop (8 GB RAM or more) with Python 3.11+ or a free cloud notebook
  • Code editor (VS Code)

Evaluación

Project assessment

Reseñas de estudiantes

Aún no hay reseñas.

Recomendado para ti

Continúa tu itinerario

Similar topic
Similar topic
Similar topic
● En vivo EN · ع En desarrollo
Inteligencia artificial y habilidades digitales

Professional Certificate in Python and Applied AI

From first Python script to practical AI applications: data analysis, machine learning ba…

60 h En vivo en línea
$1,200
Similar topic
● En vivo EN · ع En desarrollo
Inteligencia artificial y habilidades digitales

Time-Series Forecasting and Predictive Maintenance

Forecast demand and detect equipment problems early using statistical and machine-learnin…

18 h En vivo en línea
$690