Proves or disproves convergence of RL algorithms using contraction mapping, Dvoretzky, Extended Dvoretzky, and Robbins-Monro theorems.
Proves or disproves convergence of RL algorithms using contraction mapping, Dvoretzky, Extended Dvoretzky, and Robbins-Monro theorems.
Category: science-education (科学教育) · Author: chuongdlb · Version: @main · License: MIT
Tags: convergence, proof, stochastic-approximation, theory
该 Skill 暂无文档文件。
npx skills add chuongdlb/rl-convergence-prover下载完整 Skill 目录，包含 SKILL.md 及所有相关文件
Category:science-education