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 learning | Machine learning |
| 提唱年≠ | 2015 | 2017 |
| 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, DRL | Nöral Mimari Arama (NAS), NAS, automated architecture design, differentiable architecture search |
| 関連≠ | 4 | 5 |
| 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 ↗ |
|
|