ScholarGate
עוזר

השוואת שיטות

סקרו את השיטות שבחרתם זו לצד זו; שורות שבהן יש הבדל מודגשות.

למידת חיזוק×שיטות גרדיאנט מדיניות×
תחוםלמידה עמוקהלמידת מכונה
משפחהMachine learningMachine learning
שנת המקור1950s–19981992
הוגה השיטהSutton, R. S. & Barto, A. G. (formalised); Bellman, R. (foundations)Ronald Williams (REINFORCE); Sutton et al. (policy gradient theorem)
סוגSequential decision-making frameworkPolicy-based reinforcement learning
מקור מכונןSutton, 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 ↗
כינוייםRL, reward-based learning, trial-and-error learning, policy optimizationREINFORCE, actor-critic, policy optimization, politika gradyanı
קשורות24
תקצירReinforcement 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.
ScholarGateמערך נתונים
  1. v1
  2. 2 מקורות
  3. PUBLISHED
  1. v1
  2. 2 מקורות
  3. PUBLISHED

מעבר לחיפוש הורדת מצגת

ScholarGateהשוואת שיטות: Reinforcement Learning · Policy Gradient. אוחזר בתאריך 2026-06-17 מתוך https://scholargate.app/he/compare