Awesome AI Agents › Educational & Learning Agents
This repository, titled "All RL Algorithms from Scratch," is a comprehensive educational resource dedicated to the implementation and understanding of a wide range of Reinforcement Learning (RL) algorithms. The primary objective of the project is to provide clear, readable, and intuitive Python implementations of RL algorithms to help learners grasp the fundamental concepts and mechanics behind these methods without the complexity of advanced RL libraries. It emphasizes educational value over performance optimization, making it ideal for beginners and those seeking a deep understanding of RL. The repository includes implementations of 18 different RL algorithms, each presented in its own Jupyter Notebook. These algorithms cover various categories such as value-based methods (e.g., Q-Learning, SARSA), policy-based methods (e.g., REINFORCE), actor-critic methods (e.g., PPO, A2C, A3C, DDPG, SAC), model-based methods (e.g., Dyna-Q, PlaNet), hierarchical methods (e.g., HAC), multi-agent RL (e.g., MADDPG, QMIX), and planning algorithms (e.g., Monte Carlo Tree Search). Each notebook provides step-by-step explanations, code that closely mirrors the mathematical descriptions, and interactive elements for experimentation. The project also includes a comprehensive RL Cheat Sheet that summarizes key concepts, formulas, pseudocode, and algorithmic ideas, serving as a quick reference guide. The repository uses basic libraries such as NumPy, Matplotlib, and PyTorch to implement the algorithms, focusing on clarity and educational value rather than speed or advanced features. Overall, this repository serves as an interactive textbook and playground for anyone interested in learning reinforcement learning from the ground up, offering a structured and accessible approach to mastering a broad spectrum of RL techniques.
https://github.com/FareedKhan-dev/all-rl-algorithms
AI Agents for Beginners is a Microsoft educational course with 10 lessons teaching the fundamentals and practical skills to build AI agents using Azure AI and GitHub models, supported by multi-language resources and community engagement.
This repository offers a comprehensive, hands-on curriculum (503 lessons across 20 phases) for building AI systems from scratch, covering math to autonomous agents, using Python, TypeScript, Rust, ...
A comprehensive collection of free resources to learn AI, machine learning, large language models, and AI agents from scratch.
TheoremExplainAgent is an AI system that generates long-form Manim videos to visually explain mathematical theorems, enhancing understanding through multimodal explanations combining text, visuals, and audio.
Inno Agent is a personal learning agent with three explicit memory layers, a cron scheduler, Feishu and WeChat channels and a workspace-scoped practice terminal, built on the Pi coding-agent SDK.
LangChain-OpenTutorial is an open, community-driven tutorial resource providing comprehensive learning materials and practical examples for LangChain and LangGraph technologies, suitable for users of all skill levels worldwide.
Groundhog is an AI coding assistant designed as a teaching tool to help users understand and leverage the inner workings of coding agents like Cursor through detailed code explanations and a modern Rust-based CLI.
An educational repository with code and notebooks accompanying the "Quick Start Guide to Large Language Models - Second Edition" book, covering practical applications and advanced techniques for large language models.