ScholarGate
Asistent

Usporedite metode

Pregledajte odabrane metode jednu uz drugu; retci koji se razlikuju su istaknuti.

Duboko pojačavajuće učenje×Prijenosno učenje×
PodručjeDuboko učenjeStrojno učenje
ObiteljMachine learningMachine learning
Godina nastanka20152010 (formalized); 1990s (early roots)
TvoracMnih, V. et al. (DQN)Pan, S. J. & Yang, Q. (survey); Bengio, Y. (deep learning framing)
VrstaSequential decision-making (agent–environment interaction)Learning paradigm
Temeljni izvorMnih, V. et al. (2015). Human-Level Control through Deep Reinforcement Learning. Nature, 518, 529–533. DOI ↗Pan, S. J., & Yang, Q. (2010). A Survey on Transfer Learning. IEEE Transactions on Knowledge and Data Engineering, 22(10), 1345–1359. DOI ↗
Drugi naziviDerin Pekiştirmeli Öğrenme (DQN / PPO / A3C), derin pekiştirmeli öğrenme, deep RL, DRLTL, domain adaptation, fine-tuning, pre-trained model adaptation
Srodne43
SažetakDeep 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.Transfer learning is a machine learning paradigm in which knowledge gained from training a model on a source task or domain is reused to improve learning on a different but related target task or domain. It is especially powerful when labeled data for the target task is scarce, and it underlies most modern deep learning applications in computer vision, natural language processing, and beyond.
ScholarGateSkup podataka
  1. v1
  2. 2 Izvori
  3. PUBLISHED
  1. v1
  2. 2 Izvori
  3. PUBLISHED

Idi na pretraživanje Preuzmi prezentaciju

ScholarGateUsporedite metode: Deep Reinforcement Learning · Transfer Learning. Preuzeto 2026-06-18 s https://scholargate.app/hr/compare