השוואת שיטות

	שיטות גרדיאנט מדיניות	אופטימיזציה קמורה
תחום	למידת מכונה	אופטימיזציה
משפחה	Machine learning	Process / pipeline
שנת המקור	1992	2004
הוגה השיטה	Ronald Williams (REINFORCE); Sutton et al. (policy gradient theorem)	Stephen Boyd & Lieven Vandenberghe
סוג	Policy-based reinforcement learning	Mathematical optimization framework
מקור מכונן	Williams, R. J. (1992). Simple statistical gradient-following algorithms for connectionist reinforcement learning. Machine Learning, 8(3–4), 229–256.	Boyd, S., & Vandenberghe, L. (2004). Convex Optimization. Cambridge University Press. ISBN: 978-0-521-83378-3
כינויים	REINFORCE, actor-critic, policy optimization, politika gradyanı	Convex Programming, Disciplined Convex Programming, Dışbükey Optimizasyon, Convex Mathematical Programming
קשורות	4	3
תקציר	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.	Convex optimization is a subfield of mathematical optimization that studies the problem of minimizing convex functions over convex sets. Formalized and popularized by Stephen Boyd and Lieven Vandenberghe in their landmark 2004 textbook, the framework unifies a wide family of problems — including linear programming, quadratic programming, semidefinite programming, and second-order cone programming — under a single theoretical roof. Its defining property is that any locally optimal solution is also globally optimal, making it tractable and reliable for engineering, statistics, machine learning, and operations research.