手法を比較

	方策勾配法	確率的勾配降下法 (SGD)
分野	機械学習	機械学習
系統	Machine learning	Machine learning
提唱年	1992	1951
提唱者	Ronald Williams (REINFORCE); Sutton et al. (policy gradient theorem)	Robbins, H. & Monro, S.
種類	Policy-based reinforcement learning	First-order iterative optimization algorithm
原典	Williams, R. J. (1992). Simple statistical gradient-following algorithms for connectionist reinforcement learning. Machine Learning, 8(3–4), 229–256.	Robbins, H. & Monro, S. (1951). A Stochastic Approximation Method. The Annals of Mathematical Statistics, 22(3), 400–407.
別名	REINFORCE, actor-critic, policy optimization, politika gradyanı	SGD, online gradient descent, incremental gradient descent, mini-batch gradient descent
関連	4	3
概要	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.	Stochastic Gradient Descent (SGD) is a first-order iterative optimization algorithm, rooted in the stochastic approximation framework introduced by Robbins and Monro in 1951, that minimizes an objective function by updating model parameters using the gradient computed on a single randomly selected training example (or a small mini-batch) at each step. It is the core optimization engine behind modern machine learning and deep learning, enabling the training of models on datasets too large to fit in memory.