Awesome GitHub RepositoriesReinforcement Learning Optimizers

This project provides a comprehensive framework for building, training, and managing autonomous agents. It enables the construction of systems that utilize language models to plan, manage memory, and execute multi-step tasks through iterative reasoning loops and tool-based actions. The framework distinguishes itself by offering specialized capabilities for interacting with graphical user interfaces and legacy software, allowing agents to perceive visual elements and perform actions like a human user. It supports complex, cross-application workflows through graph-based orchestration and provid

This project is an educational platform and research toolkit designed to teach deep learning through a combination of mathematical theory, visual diagrams, and executable code. It provides a comprehensive environment for building, training, and evaluating neural networks, grounding complex concepts in interactive computational notebooks that allow for hands-on experimentation. The framework distinguishes itself by interleaving theoretical foundations—including linear algebra, calculus, and probability—with practical implementations across multiple industry-standard libraries. It supports flex

Open-r1 is a framework designed for the large-scale training, distillation, and optimization of language models focused on complex reasoning and programming tasks. It provides a comprehensive suite of tools for managing distributed training jobs across multi-node clusters, enabling the development of high-performance models through reinforcement learning and supervised fine-tuning. The project distinguishes itself by integrating secure, containerized code execution environments directly into the training and evaluation lifecycle. By allowing models to run and verify code snippets against test

This project is a distributed training infrastructure designed for aligning large language models through reinforcement learning. It functions as an end-to-end engine for complex alignment tasks, including proximal policy optimization, direct preference optimization, and iterative self-play. By providing a unified framework for multi-turn interactions and tool-use scenarios, it enables the development of models capable of reasoning and external environment engagement. The framework distinguishes itself through a decoupled architecture that separates model training from sample generation. This

WebAgent is an autonomous web navigation agent and research system designed to browse the internet and synthesize information to answer complex queries. It functions as a reasoning orchestrator that navigates the web iteratively to perform deep research and extract structured data. The project includes a reinforcement learning training pipeline that generates synthetic interaction datasets for model pre-training and fine-tuning. It employs token-level policy gradients to stabilize training in non-stationary environments and uses a dual-mode inference scaling mechanism to balance execution bet

This project is a comprehensive toolkit designed for the full lifecycle management of large language and multimodal models. It functions as a unified orchestrator that handles the entire development process, ranging from dataset preparation and supervised fine-tuning to advanced reinforcement learning alignment and production-ready inference deployment. The platform distinguishes itself through a specialized reinforcement learning library that supports complex optimization algorithms, including group relative policy optimization and leave-one-out techniques, to improve model instruction-follo

TinyZero is a reinforcement learning framework and implementation designed to train language models to develop reasoning and self-verification abilities. It provides a training pipeline to optimize model performance on mathematical and logical tasks. The project serves as a minimal reproduction of the DeepSeek R1 architectural and training approach. It focuses on creating reasoning models that can solve structured problems through autonomous chain-of-thought discovery. The framework incorporates group relative policy optimization and reward-based self-correction to improve accuracy on logica

Stable-baselines3 is a reinforcement learning library built on the PyTorch deep learning framework. It provides a collection of reliable, standardized implementations of reinforcement learning algorithms designed for training, testing, and benchmarking agent policies in diverse simulated environments. The library functions as an agent training toolkit that emphasizes modularity and reproducibility. It features a unified environment interface and supports vectorized execution to accelerate data collection across multiple simulation instances. Users can customize neural network architectures, f

HRM is an automated reasoning engine and language framework designed to execute complex, multi-scale problem solving. It functions as a reinforcement learning agent that continuously updates internal knowledge representations to improve task performance based on incoming data streams. The system distinguishes itself through a hierarchical architecture that coordinates abstract, long-term planning with granular, low-level logic. By integrating evolutionary algorithms and reinforcement learning, the framework refines model parameters and weights over successive generations, ensuring that intern

This project is an educational repository of reinforcement learning agents and tutorials implemented using TensorFlow. It provides a practical codebase for both model-free and model-based learning agents, designed to demonstrate how AI agents learn through trial and error. The collection features detailed implementations of various algorithmic approaches, including Deep Q-Networks and Policy Gradient methods. It specifically covers Actor-Critic architectures for continuous and discrete action spaces, alongside Proximal Policy Optimization and Deep Deterministic Policy Gradients. The framewor

Pwnagotchi is an AI-powered wireless auditor and handshake capture tool that uses deep reinforcement learning to autonomously collect wireless security handshakes and crackable key material. It serves as an automation framework for network instrumentation, adapting its operational parameters based on the local wireless environment to maximize data collection. The system distinguishes itself through distributed coordination, allowing multiple hardware units to share presence and divide wireless channels to optimize collective capture and perform distributed wireless mapping. It incorporates ge

CleanRL is a reinforcement learning library and PyTorch framework providing a suite of reproducible implementations for online reinforcement learning algorithms. It serves as a deep reinforcement learning benchmark suite and experiment orchestrator designed for research and agent development across both discrete and continuous action spaces. The project is distinguished by its single-file algorithm implementation approach, which encapsulates each algorithm in a standalone script to eliminate complex class hierarchies. This structure is paired with a system for scheduling and executing large-s

This project is a comprehensive collection of practical code examples and implementation libraries for machine learning. It provides a wide array of reference materials for building supervised, unsupervised, and reinforcement learning algorithms. The repository serves as a multi-domain resource, featuring specific implementation suites for financial AI, Bayesian statistical modeling, and deep learning architectures. It includes a framework for training intelligent agents using policy gradients and actor-critic models, as well as practical guides for fine-tuning transformers and utilizing larg

ART is a platform for agentic training, providing a reinforcement learning framework, training environment, and compute orchestrator. It enables the improvement of multi-step agent reasoning and tool usage through group relative policy optimization and a judge-based reward modeling system. The project features tools for model distillation to transfer capabilities from large teacher models to smaller architectures, as well as a system for capturing execution trajectories to generate synthetic training data. It supports specialized training workflows including supervised fine-tuning for baselin

Sana is a framework for high-resolution image and video synthesis based on a linear diffusion transformer. It provides a toolkit for the training, fine-tuning, and execution of text-to-image and text-to-video models, as well as a video generative world model capable of simulating physical environments with precise spatial control. The project is distinguished by its use of linear complexity layers to handle high resolutions and its support for long-form, minute-length video generation in real time. It implements a two-stage inference paradigm that separates structural generation from visual t

This is a PyTorch implementation of reinforcement learning from human feedback designed to align large language models with human values and preferences. It provides a framework for the PaLM architecture and incorporates parameter-efficient fine-tuning to adapt models while minimizing the number of updated weights. The system enables the development of reward models that act as scoring mechanisms built from human preference data. These models evaluate generative outputs to guide the alignment process. The workflow covers policy optimization using a clipped objective, reward modeling based on

VLM-R1 es un modelo de razonamiento visión-lenguaje y framework de IA corpórea (embodied AI) diseñado para mapear entradas visuales e instrucciones de lenguaje en puntos de navegación físicos y acciones robóticas. Funciona como un optimizador de políticas multimodal y un detector de vocabulario abierto capaz de localizar objetos basados en descripciones arbitrarias en lenguaje natural. El sistema se distingue por el uso de razonamiento de cadena de pensamiento (chain-of-thought) y aprendizaje por refuerzo para resolver tareas visuales y espaciales complejas. Utiliza un sistema de memoria semántica de video, que emplea una caché visual para mantener un historial de video en vivo para interacciones de baja latencia y razonamiento temporal continuo. El framework cubre una amplia gama de capacidades, incluyendo el mapeo de puntos de navegación monoculares para robótica, la localización de tokens de región para identificación de objetos y el ajuste fino supervisado basado en políticas para la estabilidad del razonamiento multimodal. También admite detección de vocabulario abierto, comprensión de expresiones de referencia y la extracción de características de objetos detalladas mediante recuperación de prompts visuales. El proyecto está implementado en Python y admite inferencia en hardware Ascend.

Orange3 is a visual data mining platform that provides an interactive canvas for building data analysis workflows without writing code. At its core, it offers a widget-based visual programming environment where users connect configurable components to perform data preprocessing, machine learning model training, statistical evaluation, and interactive visualization. The platform is built on NumPy-backed data tables with domain descriptors that define variable names, types, and roles, and includes a lazy SQL query proxy for working with database tables without loading all data into memory. The

rllm is an asynchronous reinforcement learning framework for training language agents. It provides a unified pipeline that runs the same agent code for both evaluation and training, automatically capturing traces for gradient computation. The framework supports distributed reinforcement learning across multiple GPUs and nodes using pluggable backends, and executes agents in isolated sandboxes—either locally or in the cloud—for safe and scalable rollout collection. It trains agents built with LangGraph, SmolAgents, OpenAI Agents SDK, or custom frameworks without requiring core logic changes. T

OpenClaw-RL es un framework de aprendizaje por refuerzo para entrenar agentes de modelos de lenguaje grandes. Proporciona un sistema para optimizar las políticas de los agentes utilizando instrucciones en lenguaje natural, optimización basada en recompensas y un pipeline para refinar el comportamiento del modelo a través de retroalimentación humana o de jueces. El framework utiliza adaptación de bajo rango (LoRA) para actualizar los pesos del modelo de manera eficiente sin un ajuste completo de parámetros. Cuenta con una infraestructura local-first que permite que el modelo de política, el juez y el entrenador se ejecuten en hardware privado para mantener la localidad de los datos. El sistema cubre una gama de capacidades de optimización, incluyendo el entrenamiento de uso de herramientas para entornos de terminal y GUI y el refinamiento de políticas conversacionales. Implementa un bucle de entrenamiento híbrido que combina recompensas escalares con destilación a nivel de token para proporcionar retroalimentación tanto densa como dispersa. Para mantener el rendimiento, emplea una arquitectura de ejecución asíncrona que desacopla el servicio del agente del proceso de entrenamiento.