قارن الطرق

	التعلم المعزز العميق	Neural Architecture Search
المجال	التعلم العميق	التعلم العميق
العائلة	Machine learning	Machine learning
سنة النشأة	2015	2017
صاحب الطريقة	Mnih, V. et al. (DQN)	Zoph, B. & Le, Q.V.
النوع	Sequential decision-making (agent–environment interaction)	Automated architecture optimization (deep learning)
المصدر التأسيسي	Mnih, V. et al. (2015). Human-Level Control through Deep Reinforcement Learning. Nature, 518, 529–533.	Zoph, B. & Le, Q.V. (2017). Neural Architecture Search with Reinforcement Learning. ICLR.
الأسماء البديلة	Derin Pekiştirmeli Öğrenme (DQN / PPO / A3C), derin pekiştirmeli öğrenme, deep RL, DRL	Nöral Mimari Arama (NAS), NAS, automated architecture design, differentiable architecture search
ذات صلة	4	5
الملخص	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.