Jump to content

Top Ideas Of ç‰§é‡Žæµ äºŒ: Revision history

Diff selection: Mark the radio buttons of the revisions to compare and hit enter or the button at the bottom.
Legend: (cur) = difference with latest revision, (prev) = difference with preceding revision, m = minor edit.

15 December 2025

  • curprev 11:4711:47, 15 December 2025 Clay49X331535 talk contribs 1,479 bytes +1,479 Created page with "<br><br><br>本书内容:介绍深度学习、强化学习和深度强化学习的基本知识。 通过多种实际对战游戏(如太空侵略者、吃豆人)来介绍算法,如ε-greedy算法。 使用Anaconda设置本地PC,在倒立摆和老鼠学习问题中实现深度强化学习。<br>使用Python实现MNIST手写数字分类任务。 详解继DQN之后提出的新的深度强化学习技术(DDQN、PER-DQN、DDPG和A3C等)。<br>本書面向普通..."