Model-free (reinforcement learning)
id:
model-free-reinforcement-learning-306-13169896
title:
Model-free (reinforcement learning)
text:
In reinforcement learning (RL), a model-free algorithm is an algorithm which does not estimate the transition probability distribution associated with the Markov decision process (MDP), which, in RL, represents the problem to be solved. The transition probability distribution and the reward function are often collectively called the "model" of the environment, hence the name "model-free". A model-free RL algorithm can be thought of as an "explicit" trial-and-error algorithm. Typical examples of
brand slug:
wiki
category slug:
encyclopedia
description:
Type of machine learning algorithm
original url:
https://en.wikipedia.org/wiki/Model-free_(reinforcement_learning)
date created:
date modified:
2023-12-20T09:02:29Z
main entity:
{"identifier":"Q63788448","url":"https://www.wikidata.org/entity/Q63788448"}
image:
fields total:
13
integrity:
14