Next ForgeOpenTech
書籍

目次

  • 00_Overview_of_this_Book
  • 01_Basic_Concepts
  • 02_State_Values_and_Bellman_Equation
  • 03_Optimal_State_Values_and_Bellman_Optimality_Equation
  • 04_Value_Iteration_and_Policy_Iteration
  • 05_Monte_Carlo_Methods
  • 06_Stochastic_Approximation
  • 07_Temporal-Difference_Methods
  • 08_Value_Function_Methods
  • 09_Policy_Gradient_Methods
  • 10_Actor-Critic_Methods
  • 11_A_Preliminaries_for_Probability_Theory
  • 12_B_Measure-Theoretic_Probability_Theory
  • 13_C_Convergence_of_Sequences
  • 14_D_Preliminaries_for_Gradient_Descent
  • 15_Bibliography
  • 16_Symbols
  • 17_Index

README

Convergence of Sequences

We next introduce some results about the convergence of deterministic and stochastic sequences. These results are useful for analyzing the convergence of reinforcement learning algorithms such as those in Chapters 6 and 7.

We first consider deterministic sequences and then stochastic sequences.

前の章13_C_Convergence_of_Sequences
次の章C.1_Convergence_of_deterministic_sequences

OpenTech

AI駆動の読書・学習プラットフォーム

Built withLogoNexty.dev

言語

  • English
  • 中文
  • 日本語

オープンソースプロジェクト

  • Next Forge
  • Landing Page Boilerplate
  • Blog Boilerplate

その他の製品

  • Nexty - SaaS Template
  • OG Image Generator
  • Dofollow.Tools

Next Forgeのニュースレターに登録する

Next Forgeの最新のニュースと更新情報を入手します。

Copyright © 2025 Next Forge All rights reserved.

プライバシーポリシー利用規約
Featured on Dofollow.Tools