TERMIUM Plus®

From: Translation Bureau

On social media

Consult the Government of Canada’s terminology data bank.

APPRENTISSAGE RENFORCEMENT RETROACTION HUMAINE [1 record]

Record 1 2025-09-25

English

Subject field(s)
  • Artificial Intelligence
OBS

Reinforcement learning from human feedback is used to align a pre-trained machine learning model with a specific task or behaviour. For this purpose, it relies on evaluations of the model's output by humans. The results of these evaluations are often provided to the model in the form of rewards and penalties.

French

Domaine(s)
  • Intelligence artificielle
OBS

L'apprentissage par renforcement à partir de la rétroaction humaine permet d'adapter un modèle d'apprentissage automatique préentraîné à une tâche ou à un comportement déterminé. Pour ce faire, cette technique se fonde sur les évaluations réalisées par des humains quant aux sorties produites par le modèle. Les résultats de ces évaluations sont souvent fournis au modèle sous forme de récompenses et de pénalités.

Spanish

Save record 1

Copyright notice for the TERMIUM Plus® data bank

© Public Services and Procurement Canada, 2026
TERMIUM Plus®, the Government of Canada's terminology and linguistic data bank
A product of the Translation Bureau

Features

GCtranslate (available on the Government of Canada network only)

Use this artificial intelligence prototype to translate Government of Canada content up to and including Protected B. Available to employees of selected departments and agencies only.

Writing tools

The Language Portal’s writing tools have a new look! Easy to consult, they give you access to a wealth of information that will help you write better in English and French.

Glossaries and vocabularies

Access Translation Bureau glossaries and vocabularies.

Date Modified: