reinforcement learning

English

Noun

reinforcement learning (uncountable)

  1. (education, psychology): Learning that occurs through reinforcement, especially through rewards, encouragement, or other consequences that strengthen desired behaviours.
  2. (machine learning) A machine-learning paradigm in which a model or agent learns by taking actions and receiving reward signals that indicate how well those actions achieve a desired objective.
    Synonym: RL
    Hypernyms: DL, deep learning < ML, machine learning < learning
    • 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.
    • 2026, Sebastian Mallaby, chapter 2, in The Infinity Machine: Demis Hassabis, DeepMind and the Quest for Superintelligence, Penguin, →ISBN:
      This basic “reinforcement learning” system was a small step in the direction of AI: a program that adjusted its program—that was capable of learning.

Derived terms

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

Translations

Further reading