ScholarGate
Assistente

Confronta i metodi

Esamina i metodi selezionati fianco a fianco; le righe che differiscono sono evidenziate.

Metodi basati sul gradiente di policy×Q-Learning×
CampoApprendimento automaticoApprendimento automatico
FamigliaMachine learningMachine learning
Anno di origine19921992
IdeatoreRonald Williams (REINFORCE); Sutton et al. (policy gradient theorem)Christopher Watkins & Peter Dayan
TipoPolicy-based reinforcement learningModel-free reinforcement-learning control algorithm
Fonte seminaleWilliams, R. J. (1992). Simple statistical gradient-following algorithms for connectionist reinforcement learning. Machine Learning, 8(3–4), 229–256. DOI ↗Watkins, C. J. C. H., & Dayan, P. (1992). Q-learning. Machine Learning, 8(3–4), 279–292. DOI ↗
AliasREINFORCE, actor-critic, policy optimization, politika gradyanıQ-learning algorithm, tabular Q-learning, off-policy TD control, Q-öğrenme
Correlati43
SintesiPolicy 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.Q-learning, introduced by Christopher Watkins and Peter Dayan in 1992, is a model-free reinforcement-learning algorithm that learns the value of taking each action in each state — the Q-function — purely from experience, without a model of the environment. It is off-policy: it learns the optimal action-values while following an exploratory behaviour policy, and under standard conditions it provably converges to the optimal policy.
ScholarGateInsieme di dati
  1. v1
  2. 2 Fonti
  3. PUBLISHED
  1. v1
  2. 2 Fonti
  3. PUBLISHED

Vai alla ricerca Scarica le diapositive

ScholarGateConfronta i metodi: Policy Gradient · Q-Learning. Consultato il 2026-06-15 da https://scholargate.app/it/compare