ScholarGate
Βοηθός

Σύγκριση μεθόδων

Εξετάστε τις επιλεγμένες μεθόδους δίπλα-δίπλα· οι γραμμές που διαφέρουν επισημαίνονται.

Ενισχυτική Μάθηση×Μέθοδοι Κλίσης Πολιτικής×
ΠεδίοΒαθιά ΜάθησηΜηχανική Μάθηση
ΟικογένειαMachine learningMachine learning
Έτος προέλευσης1950s–19981992
ΔημιουργόςSutton, R. S. & Barto, A. G. (formalised); Bellman, R. (foundations)Ronald Williams (REINFORCE); Sutton et al. (policy gradient theorem)
ΤύποςSequential decision-making frameworkPolicy-based reinforcement learning
Θεμελιώδης πηγήSutton, R. S. & Barto, A. G. (2018). Reinforcement Learning: An Introduction (2nd ed.). MIT Press. ISBN: 978-0-262-03924-6Williams, R. J. (1992). Simple statistical gradient-following algorithms for connectionist reinforcement learning. Machine Learning, 8(3–4), 229–256. DOI ↗
Εναλλακτικές ονομασίεςRL, reward-based learning, trial-and-error learning, policy optimizationREINFORCE, actor-critic, policy optimization, politika gradyanı
Συναφείς24
ΣύνοψηReinforcement Learning (RL) is a framework in which an agent learns to make sequential decisions by interacting with an environment, receiving scalar reward signals, and updating a policy to maximise cumulative future reward. Unlike supervised learning, no labeled examples are provided; the agent discovers optimal behavior entirely through experience and delayed feedback.Policy 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.
ScholarGateΣύνολο δεδομένων
  1. v1
  2. 2 Πηγές
  3. PUBLISHED
  1. v1
  2. 2 Πηγές
  3. PUBLISHED

Μετάβαση στην αναζήτηση Λήψη διαφανειών

ScholarGateΣύγκριση μεθόδων: Reinforcement Learning · Policy Gradient. Ανακτήθηκε στις 2026-06-17 από https://scholargate.app/el/compare