Ir para o conteúdo
Atlas de IA

Aprendizado por reforço

Aprender sequências de decisões por tentativa, erro e recompensa atrasada

OVERVIEW

Todos os conceitos
6
Iniciante
2
Intermediário
3
Especialista
1

Reinforcement learning addresses problems that have no answer key, only consequences: whether a step was good may only be revealed much later as reward. It introduces the vocabulary of agent, environment, state, action and reward, and approaches optimal behaviour through two families of ideas — value functions and policy gradients.