Machine learningReinforcement learning
策略梯度方法
策略梯度方法是强化学习算法，它们通过对期望回报进行梯度上升来直接优化参数化策略，而不是学习动作价值并采取贪婪策略。该方法基于 Ronald Williams 于 1992 年提出的 REINFORCE 算法以及 Sutton 等人（2000 年）的策略梯度定理，能够自然地处理随机和连续动作空间，并支撑着现代的 Actor-Critic 和深度强化学习算法。
阅读完整方法
仅限会员
登录使用免费账户登录即可阅读本节。
Method map
The neighbourhood of related methods — select a node to explore.
来源
- Williams, R. J. (1992). Simple statistical gradient-following algorithms for connectionist reinforcement learning. Machine Learning, 8(3–4), 229–256. DOI: 10.1007/BF00992696 ↗
- Sutton, R. S., McAllester, D., Singh, S., & Mansour, Y. (2000). Policy gradient methods for reinforcement learning with function approximation. Advances in Neural Information Processing Systems, 12, 1057–1063. link ↗
如何引用本页
ScholarGate. (2026, June 2). Policy Gradient Methods (REINFORCE / Actor-Critic). ScholarGate. https://scholargate.app/zh/machine-learning/policy-gradient
Which method?
Set this method beside its closest kin and read them side by side — the library lays the books on the table; the choice is yours.
Compare side by side →