ScholarGate
Assistent

Sammenlign metoder

Gjennomgå de valgte metodene side om side; rader som avviker, er uthevet.

Policy Gradient-metoder×Dyp forsterkningslæring×
FagfeltMaskinlæringDyp læring
FamilieMachine learningMachine learning
Opprinnelsesår19922015
OpphavspersonRonald Williams (REINFORCE); Sutton et al. (policy gradient theorem)Mnih, V. et al. (DQN)
TypePolicy-based reinforcement learningSequential decision-making (agent–environment interaction)
Opprinnelig kildeWilliams, 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 ↗
AliasREINFORCE, actor-critic, policy optimization, politika gradyanıDerin Pekiştirmeli Öğrenme (DQN / PPO / A3C), derin pekiştirmeli öğrenme, deep RL, DRL
Relaterte44
SammendragPolicy 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.
ScholarGateDatasett
  1. v1
  2. 2 Kilder
  3. PUBLISHED
  1. v1
  2. 2 Kilder
  3. PUBLISHED

Gå til søk Last ned lysbilder

ScholarGateSammenlign metoder: Policy Gradient · Deep Reinforcement Learning. Hentet 2026-06-17 fra https://scholargate.app/no/compare