ScholarGate
Ассистент

Сравнение методов

Просматривайте выбранные методы рядом; строки с различиями подсвечены.

Слабо контролируемое обучение с подкреплением×Обучение с подкреплением×
ОбластьГлубокое обучениеГлубокое обучение
СемействоMachine learningMachine learning
Год появления2010s–present1950s–1998
Автор методаMultiple contributors; reward-learning framing: Christiano et al. (2017)Sutton, R. S. & Barto, A. G. (formalised); Bellman, R. (foundations)
ТипReinforcement learning with imperfect or partial reward supervisionSequential decision-making framework
Основополагающий источникSutton, R. S. & Barto, A. G. (2018). Reinforcement Learning: An Introduction (2nd ed.). MIT Press. ISBN: 978-0-262-03924-6Sutton, R. S. & Barto, A. G. (2018). Reinforcement Learning: An Introduction (2nd ed.). MIT Press. ISBN: 978-0-262-03924-6
Другие названияWSRL, weak-reward RL, imperfect-reward reinforcement learning, reward-impoverished RLRL, reward-based learning, trial-and-error learning, policy optimization
Связанные32
СводкаWeakly supervised reinforcement learning (WSRL) trains agents in environments where the reward signal is imperfect, sparse, delayed, or only partially informative — unlike dense fully-supervised RL. The agent must learn effective policies despite incomplete feedback, using auxiliary signals, reward modeling, or preference learning to compensate for the weak supervision.Reinforcement Learning (RL) is a framework in which an agent learns to make sequential decisions by interacting with an environment, receiving scalar reward signals, and updating a policy to maximise cumulative future reward. Unlike supervised learning, no labeled examples are provided; the agent discovers optimal behavior entirely through experience and delayed feedback.
ScholarGateНабор данных
  1. v1
  2. 2 Источники
  3. PUBLISHED
  1. v1
  2. 2 Источники
  3. PUBLISHED

Перейти к поиску Скачать слайды

ScholarGateСравнение методов: Weakly supervised reinforcement learning · Reinforcement Learning. Получено 2026-06-15 из https://scholargate.app/ru/compare