Awesome GitHub RepositoriesRL Agent Implementation Frameworks

Dopamine is a reinforcement learning research framework designed for prototyping and testing algorithms across diverse simulated environments. It provides an agent development toolkit that utilizes a flat class hierarchy to facilitate the creation and extension of learning agents. The framework includes a standardization layer via environment wrappers that connect agents to various physics simulations and gaming environments. It also features a high-performance experience replay buffer for storing and sampling transition data to improve training stability, alongside a dedicated hyperparameter

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

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

keras-rl is a reinforcement learning library that enables the training of neural agents using Keras. It serves as a framework for implementing deep reinforcement learning agents that interact with simulated environments to discover optimal behaviors and maximize cumulative rewards. The library provides a system for configuring, training, and managing neural network agents. It handles the interaction loop between agents and environments, allowing models to learn through direct experience and gradient-based optimization. The framework includes capabilities for model weight management, allowing

Este proyecto es un plan de estudios de aprendizaje por refuerzo profundo que proporciona materiales educativos y ejercicios de implementación para dominar agentes basados en redes neuronales. Sirve como un framework para construir versiones de referencia de métodos basados en valores y basados en políticas para resolver problemas de decisión secuenciales. El proyecto proporciona implementaciones específicas para simulaciones de control continuo y aprendizaje por refuerzo multi-agente, donde los agentes son entrenados para cooperar o competir en entornos compartidos. Incluye un framework de gradiente de política para optimizar el comportamiento del agente a través de métodos como REINFORCE. Las capacidades cubren una amplia gama de algoritmos de optimización, incluyendo aprendizaje Q profundo, gradientes de política deterministas y programación dinámica para el modelado de procesos de decisión de Markov. El sistema admite varios dominios de entrenamiento, como navegación robótica, automatización de comercio financiero y simulaciones basadas en física. Los materiales se entregan como una serie de Jupyter Notebooks.

Verifiers is a reinforcement learning environment framework and evaluation toolkit designed to train and evaluate large language models. It provides a standardized system for constructing simulation environments, managing training harnesses, and tracking agent trajectories through multi-turn interactions. The project features a dedicated agent trajectory manager to handle branching rollouts and token sequences, alongside an evaluation toolkit that tests model outputs against defined reward rubrics and datasets. It includes capabilities for reward engineering and the ability to package environ

SLIME is a distributed reinforcement learning framework for large language model post-training that bridges Megatron training with SGLang inference servers. It orchestrates scalable RL loops across GPU clusters, decoupling training and inference into independent processes that communicate over HTTP and NCCL for independent scaling and fault tolerance. The system supports multi-agent reinforcement learning workflows with parallel agent instances, customizable rollout strategies, and personalized agent serving that improves models from prior conversations without disrupting API serving. The fra

Acme es un framework de aprendizaje por refuerzo y motor de ejecución diseñado para desarrollar y realizar benchmarks de algoritmos de aprendizaje. Proporciona una biblioteca de componentes modulares e implementaciones de referencia utilizadas para construir agentes y establecer líneas base de rendimiento. El sistema permite escalar arquitecturas de agentes desde la ejecución de flujo único hasta grandes entornos distribuidos. Esto facilita la transición desde el prototipado inicial hasta la ejecución distribuida para entrenamiento y evaluación. El framework cubre el desarrollo de aprendizaje por refuerzo y el prototipado de arquitecturas de agentes, proporcionando los bloques de construcción necesarios para comparar nuevos modelos frente a agentes de referencia estándar.

This project is a collection of pretrained reinforcement learning agents and training scripts built on Stable Baselines3 and Gymnasium. It provides a framework for training agents to solve specific tasks, managing experiment reproducibility, and deploying pretrained models. The system includes a specialized benchmarking suite and optimization tools for tuning agent settings. It utilizes automated search spaces and distributed trials to maximize performance, while employing bootstrap sampling to generate statistically robust performance metrics and confidence intervals. Broad capabilities cov