ScholarGate
Assistente

Confronta i metodi

Esamina i metodi selezionati fianco a fianco; le righe che differiscono sono evidenziate.

Apprendimento per Rinforzo Profondo×Ricerca Architetturale Neurale×
CampoApprendimento profondoApprendimento profondo
FamigliaMachine learningMachine learning
Anno di origine20152017
IdeatoreMnih, V. et al. (DQN)Zoph, B. & Le, Q.V.
TipoSequential decision-making (agent–environment interaction)Automated architecture optimization (deep learning)
Fonte seminaleMnih, V. et al. (2015). Human-Level Control through Deep Reinforcement Learning. Nature, 518, 529–533. DOI ↗Zoph, B. & Le, Q.V. (2017). Neural Architecture Search with Reinforcement Learning. ICLR. link ↗
AliasDerin Pekiştirmeli Öğrenme (DQN / PPO / A3C), derin pekiştirmeli öğrenme, deep RL, DRLNöral Mimari Arama (NAS), NAS, automated architecture design, differentiable architecture search
Correlati45
SintesiDeep 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.Neural Architecture Search (NAS), introduced by Zoph and Le in 2017, automatically optimizes architectural decisions such as a network's depth, width, and connection structure instead of hand-designing them. Leading methods in the field include DARTS, ENAS, and Once-for-All.
ScholarGateInsieme di dati
  1. v1
  2. 2 Fonti
  3. PUBLISHED
  1. v1
  2. 2 Fonti
  3. PUBLISHED

Vai alla ricerca Scarica le diapositive

ScholarGateConfronta i metodi: Deep Reinforcement Learning · Neural Architecture Search. Consultato il 2026-06-18 da https://scholargate.app/it/compare