ScholarGate
Asystent

Porównaj metody

Przeglądaj wybrane metody obok siebie; wiersze, które się różnią, są wyróżnione.

Metody gradientu polityki×Głębokie uczenie ze wzmocnieniem×
DziedzinaUczenie maszynoweUczenie głębokie
RodzinaMachine learningMachine learning
Rok powstania19922015
TwórcaRonald Williams (REINFORCE); Sutton et al. (policy gradient theorem)Mnih, V. et al. (DQN)
TypPolicy-based reinforcement learningSequential decision-making (agent–environment interaction)
Źródło pierwotneWilliams, R. J. (1992). Simple statistical gradient-following algorithms for connectionist reinforcement learning. Machine Learning, 8(3–4), 229–256. DOI ↗Mnih, V. et al. (2015). Human-Level Control through Deep Reinforcement Learning. Nature, 518, 529–533. DOI ↗
Inne nazwyREINFORCE, actor-critic, policy optimization, politika gradyanıDerin Pekiştirmeli Öğrenme (DQN / PPO / A3C), derin pekiştirmeli öğrenme, deep RL, DRL
Pokrewne44
PodsumowaniePolicy gradient methods are reinforcement-learning algorithms that optimize a parameterized policy directly by gradient ascent on the expected return, rather than learning action-values and acting greedily. Founded on Ronald Williams' 1992 REINFORCE algorithm and the policy gradient theorem of Sutton and colleagues (2000), they naturally handle stochastic and continuous action spaces and underpin modern actor-critic and deep-RL algorithms.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.
ScholarGateZbiór danych
  1. v1
  2. 2 Źródła
  3. PUBLISHED
  1. v1
  2. 2 Źródła
  3. PUBLISHED

Przejdź do wyszukiwania Pobierz slajdy

ScholarGatePorównaj metody: Policy Gradient · Deep Reinforcement Learning. Pobrano 2026-06-17 z https://scholargate.app/pl/compare