השוואת שיטות

	שיטות גרדיאנט מדיניות	למידת Q
תחום	למידת מכונה	למידת מכונה
משפחה	Machine learning	Machine learning
שנת המקור	1992	1992
הוגה השיטה	Ronald Williams (REINFORCE); Sutton et al. (policy gradient theorem)	Christopher Watkins & Peter Dayan
סוג	Policy-based reinforcement learning	Model-free reinforcement-learning control algorithm
מקור מכונן	Williams, R. J. (1992). Simple statistical gradient-following algorithms for connectionist reinforcement learning. Machine Learning, 8(3–4), 229–256.	Watkins, C. J. C. H., & Dayan, P. (1992). Q-learning. Machine Learning, 8(3–4), 279–292.
כינויים	REINFORCE, actor-critic, policy optimization, politika gradyanı	Q-learning algorithm, tabular Q-learning, off-policy TD control, Q-öğrenme
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.	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.