Comparer des méthodes

	Apprentissage par renforcement	Méthodes de gradient de politique
Domaine	Apprentissage profond	Apprentissage automatique
Famille	Machine learning	Machine learning
Année d'origine	1950s–1998	1992
Auteur d'origine	Sutton, R. S. & Barto, A. G. (formalised); Bellman, R. (foundations)	Ronald Williams (REINFORCE); Sutton et al. (policy gradient theorem)
Type	Sequential decision-making framework	Policy-based reinforcement learning
Source fondatrice	Sutton, R. S. & Barto, A. G. (2018). Reinforcement Learning: An Introduction (2nd ed.). MIT Press. ISBN: 978-0-262-03924-6	Williams, R. J. (1992). Simple statistical gradient-following algorithms for connectionist reinforcement learning. Machine Learning, 8(3–4), 229–256.
Alias	RL, reward-based learning, trial-and-error learning, policy optimization	REINFORCE, actor-critic, policy optimization, politika gradyanı
Apparentées	2	4
Résumé	Reinforcement 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.