ScholarGate
Ассистент

Сравнение методов

Просматривайте выбранные методы рядом; строки с различиями подсвечены.

Глубокое обучение с подкреплением×Методы градиента политики×
ОбластьГлубокое обучениеМашинное обучение
СемействоMachine learningMachine learning
Год появления20151992
Автор методаMnih, V. et al. (DQN)Ronald Williams (REINFORCE); Sutton et al. (policy gradient theorem)
ТипSequential decision-making (agent–environment interaction)Policy-based reinforcement learning
Основополагающий источникMnih, V. et al. (2015). Human-Level Control through Deep Reinforcement Learning. Nature, 518, 529–533. DOI ↗Williams, R. J. (1992). Simple statistical gradient-following algorithms for connectionist reinforcement learning. Machine Learning, 8(3–4), 229–256. DOI ↗
Другие названияDerin Pekiştirmeli Öğrenme (DQN / PPO / A3C), derin pekiştirmeli öğrenme, deep RL, DRLREINFORCE, actor-critic, policy optimization, politika gradyanı
Связанные44
СводкаDeep Reinforcement Learning combines neural networks with reinforcement learning so an agent learns by interacting with an environment, popularised by Mnih and colleagues' 2015 Nature work on human-level Atari control. Instead of learning from a fixed labelled dataset, the agent takes actions, observes rewards, and gradually shapes a policy that maximises long-run return.Policy gradient methods are reinforcement-learning algorithms that optimize a parameterized policy directly by gradient ascent on the expected return, rather than learning action-values and acting greedily. Founded on Ronald Williams' 1992 REINFORCE algorithm and the policy gradient theorem of Sutton and colleagues (2000), they naturally handle stochastic and continuous action spaces and underpin modern actor-critic and deep-RL algorithms.
ScholarGateНабор данных
  1. v1
  2. 2 Источники
  3. PUBLISHED
  1. v1
  2. 2 Источники
  3. PUBLISHED

Перейти к поиску Скачать слайды

ScholarGateСравнение методов: Deep Reinforcement Learning · Policy Gradient. Получено 2026-06-17 из https://scholargate.app/ru/compare