reinforcement learning

English

Noun

reinforcement learning (uncountable)

1. (machine learning) A type of explorative learning via feedback in a simulated environment.

   Synonym: RL

   • 2010, Lutz Frommberger, Qualitative Spatial Abstraction in Reinforcement Learning, Springer Science & Business Media, →ISBN, page 10:

     Reinforcement learning can be seen as somewhere between supervised and unsupervised learning. The learning system receives a feedback for its actions, but it is not provided with examples to learn from.

   • 2022, Aske Plaat, Deep Reinforcement Learning, Springer Nature, →ISBN, page 3:

     Let us look more deeply at reinforcement learning, to see what it means to learn from our own actions. Reinforcement learning is a field in which an agent learns by interacting with an environment.

Derived terms

• DRL (“deep reinforcement learning”)
• RLAIF (“reinforcement learning from AI feedback”)
• RLHF (“reinforcement learning from human feedback”)

Translations

Translations

Bulgarian: обучение с утвърждение n (obučenie s utvǎrždenie) Chinese: Mandarin: 強化學習 / 强化学习 (qiánghuà xuéxí) Finnish: vahvistusoppiminen French: apprentissage par renforcement (fr) m German: bestärkendes Lernen n Italian: apprendimento per rinforzo m Norwegian: Bokmål: forsterkende læring f Polish: uczenie przez wzmacnianie n, uczenie posiłkowane n Swedish: förstärkningsinlärning c

Further reading

• reinforcement learning on Wikipedia.Wikipedia