Reinforcement Learning for Sequential Decision and Optimal Control

Podržano učenje

[[Datoteka:Reinforcement_learning_diagram.svg|desno|mini|250x250piksel|Tipični scenario u podržanom učenju: agent preduzima akcije u okruženju, što se tumači kao nagrada…

Reinforcement learning (pemelajaran mesin)

Reinforcement learning (RL) adalah suatu bidang interdisipliner dalam pemelajaran mesin dan kontrol optimal yang berkaitan dengan bagaimana suatu agen cerdas dapat…

Q-learning

Q-learning is a model-free reinforcement learning algorithm to learn the value of an action in a particular state.

Model-free (reinforcement learning)

In reinforcement learning (RL), a model-free algorithm (as opposed to a model-based one) is an algorithm which does not estimate the transition probability distribution (a…