ScholarGate
Асистент

Порівняння методів

Переглядайте обрані методи поруч; рядки з відмінностями підсвічено.

Глибоке навчання з підкріпленням×Рекурентна нейронна мережа×
ГалузьГлибоке навчанняГлибоке навчання
РодинаMachine learningMachine learning
Рік появи20151986–1990
Автор методуMnih, V. et al. (DQN)Rumelhart, D. E.; Elman, J. L.
ТипSequential decision-making (agent–environment interaction)Sequential neural network
Основоположне джерелоMnih, V. et al. (2015). Human-Level Control through Deep Reinforcement Learning. Nature, 518, 529–533. DOI ↗Elman, J. L. (1990). Finding structure in time. Cognitive Science, 14(2), 179–211. DOI ↗
Інші назвиDerin Pekiştirmeli Öğrenme (DQN / PPO / A3C), derin pekiştirmeli öğrenme, deep RL, DRLRNN, Elman network, Jordan network, simple recurrent network
Пов'язані43
ПідсумокDeep 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.A Recurrent Neural Network (RNN) is a class of neural network designed to process sequential data by maintaining a hidden state that carries information across time steps. Introduced in its modern form by Rumelhart et al. (1986) and further shaped by Elman (1990), RNNs became the dominant architecture for sequence modelling in NLP, speech, and time-series analysis before the rise of attention-based models.
ScholarGateНабір даних
  1. v1
  2. 2 Джерела
  3. PUBLISHED
  1. v1
  2. 2 Джерела
  3. PUBLISHED

Перейти до пошуку Завантажити слайди

ScholarGateПорівняння методів: Deep Reinforcement Learning · Recurrent Neural Network. Отримано 2026-06-18 з https://scholargate.app/uk/compare