ScholarGate
アシスタント

手法を比較

選択した手法を並べて確認できます。異なる行はハイライト表示されます。

深層強化学習×ニューラルアーキテクチャ探索×
分野深層学習深層学習
系統Machine learningMachine learning
提唱年20152017
提唱者Mnih, V. et al. (DQN)Zoph, B. & Le, Q.V.
種類Sequential decision-making (agent–environment interaction)Automated architecture optimization (deep learning)
原典Mnih, 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 ↗
別名Derin Pekiştirmeli Öğrenme (DQN / PPO / A3C), derin pekiştirmeli öğrenme, deep RL, DRLNöral Mimari Arama (NAS), NAS, automated architecture design, differentiable architecture search
関連45
概要Deep 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.
ScholarGateデータセット
  1. v1
  2. 2 出典
  3. PUBLISHED
  1. v1
  2. 2 出典
  3. PUBLISHED

検索へ スライドをダウンロード

ScholarGate手法を比較: Deep Reinforcement Learning · Neural Architecture Search. 2026-06-18に以下より取得 https://scholargate.app/ja/compare