---
title: "Wakilan koyon ƙarfafawa mai zurfi · Artificial systems · Halittu · Hasashen Kwaikwayo"
url: https://simulation-hypothesis.com/ha/entities/ai-drl
description: "Hanyoyin sadarwa na jijiyoyi da aka horar ta gwaji da kuskure don ƙara siginar lada."
license: https://creativecommons.org/licenses/by/4.0/
credit: "Ross Allan Dahl, Hasashen Kwaikwayo (simulation-hypothesis.com)"
---

[Halittu](https://simulation-hypothesis.com/ha/entities) › Tsarin wucin gadi

# Wakilan koyon ƙarfafawa mai zurfi

Hanyoyin sadarwa na jijiyoyi da aka horar ta gwaji da kuskure don ƙara siginar lada. Suna koyon manufa ko aikin ƙima ta hulɗa da muhalli, sau da yawa na kwaikwayo kamar wasa.

Hanyoyin sadarwa na jijiyoyi da aka horar ta gwaji da kuskure don ƙara siginar lada. Suna koyon manufa ko aikin ƙima ta hulɗa da muhalli, sau da yawa na kwaikwayo kamar wasa. Za su iya kaiwa ƙwarewar da ta fi ta ɗan Adam a ayyuka ƙunƙunta, amma an inganta su ne don manufar lada guda ɗaya.

## Tushe

* Mnih V, Kavukcuoglu K, Silver D, Rusu AA, et al. (2015) Human-level control through deep reinforcement learning. Nature 518(7540):529-533\. doi:10.1038/nature14236.
* Silver D et al. (2016). Mastering the game of Go with deep neural networks and tree search. Nature 529:484-489\. doi:10.1038/nature16961.

Auna shi bisa ma’aunan da aka buga