השוואת שיטות

	למידת Q	תכנון דינמי	שיטות גרדיאנט מדיניות
תחום	למידת מכונה	אופטימיזציה	למידת מכונה
משפחה	Machine learning	Process / pipeline	Machine learning
שנת המקור	1992	1957	1992
הוגה השיטה	Christopher Watkins & Peter Dayan	Richard Bellman	Ronald Williams (REINFORCE); Sutton et al. (policy gradient theorem)
סוג	Model-free reinforcement-learning control algorithm	Exact combinatorial optimization via recursive decomposition	Policy-based reinforcement learning
מקור מכונן	Watkins, C. J. C. H., & Dayan, P. (1992). Q-learning. Machine Learning, 8(3–4), 279–292.	Bellman, R. (1957). Dynamic Programming. Princeton University Press. ISBN: 978-0-691-07951-6	Williams, R. J. (1992). Simple statistical gradient-following algorithms for connectionist reinforcement learning. Machine Learning, 8(3–4), 229–256.
כינויים	Q-learning algorithm, tabular Q-learning, off-policy TD control, Q-öğrenme	DP, Bellman's Principle of Optimality, Recursive Optimization, Dinamik Programlama	REINFORCE, actor-critic, policy optimization, politika gradyanı
קשורות	3	3	4
תקציר	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.	Dynamic Programming (DP) is an exact optimization technique introduced by Richard Bellman in 1957 for solving multi-stage decision problems. It decomposes a complex problem into simpler, overlapping subproblems, solves each subproblem once, and stores the results to avoid redundant computation. Grounded in the Principle of Optimality, DP guarantees globally optimal solutions whenever the problem exhibits overlapping subproblems and optimal substructure.	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.