Open-source alternatives to Baselines

RLinf is a distributed reinforcement learning orchestrator and embodied AI training framework. It provides the infrastructure to train vision-language-action models and robotic policies using a combination of reinforcement learning and supervised fine-tuning. The system is designed for scaling workloads across GPU clusters, managing the placement of actors, rollout workers, and environment components. It features a specialized robotics data collection pipeline for gathering teleoperated demonstrations and simulation trajectories into standardized replay buffers, alongside a hardware interface

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

This project is a deep reinforcement learning curriculum providing educational materials and implementation exercises for mastering neural network-based agents. It serves as a framework for building reference versions of value-based and policy-based methods to solve sequential decision problems. The project provides specific implementations for continuous control simulations and multi-agent reinforcement learning, where agents are trained to cooperate or compete in shared environments. It includes a policy gradient framework for optimizing agent behavior through methods such as REINFORCE. Ca

Horizon is a reinforcement learning platform designed for training, evaluating, and deploying agents and contextual bandits using historical data. It serves as an off-policy engine and offline policy evaluation tool, allowing decision-making policies to be optimized and tested without the need for a live simulator. The framework specializes in recommendation system optimization, specifically using slating-based reinforcement learning to optimize the ordering and sequencing of multiple recommendations. It also functions as a contextual bandit framework that manages the balance between explorat

This repository provides a comprehensive library of reinforcement learning algorithms designed for training autonomous agents. It serves as a research-oriented collection of implementations that cover fundamental decision-making strategies, including dynamic programming, temporal difference learning, and policy gradient methods. The project distinguishes itself by offering specialized frameworks for deep reinforcement learning and structured decision modeling. It includes implementations for deep Q-learning that utilize neural networks, experience replay, and prioritized sampling to approxima

This is a PyTorch-based toolkit for training reinforcement learning agents, providing implementations of standard and hierarchical deep RL algorithms. It is designed as a library for deep reinforcement learning research and experimentation, supporting both discrete and continuous control tasks through a collection of algorithm implementations. The project distinguishes itself by offering a hierarchical reinforcement learning framework that decomposes complex long-horizon tasks into manageable sub-goals using meta-controllers and lower-level policies. It also includes a Hindsight Experience Re

Isaac Lab is an open-source framework for training robot policies in physically simulated environments, supporting both single-agent and multi-agent reinforcement learning. It is built on an Omniverse-PhysX simulation backend that models rigid bodies, articulated systems, deformable objects, and sensors, and provides a task-based environment configuration system where each training environment is defined as a modular class specifying observation spaces, action spaces, reward functions, and termination conditions. The framework distinguishes itself through an RL-library abstraction layer that

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

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

TensorLayer is a backend-agnostic tensor library and deep learning framework designed for building neural network architectures. It provides a neural network abstraction layer that allows model logic to run across different deep learning engines using high-level layers and model components. The project serves as a deep reinforcement learning toolkit for implementing policy-based, value-based, and actor-critic agents. It includes specialized tools for managing experience replay and gradient-based policy optimization to handle both discrete and continuous action spaces. To support reinforcemen

This repository is a comprehensive collection of instructional guides and practical examples for Python development, focusing on machine learning, data science, and web scraping. It provides implementations for neural networks, reinforcement learning algorithms, and deep learning architectures using PyTorch, alongside detailed manuals for scientific computing and data visualization. The project distinguishes itself by offering specialized tutorials on concurrent programming to optimize CPU performance and guides for setting up Linux development environments. It covers the implementation of ad

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

DRL is a curated educational resource that teaches deep reinforcement learning through a structured series of lectures and videos. It covers the three main families of reinforcement learning methods: actor-critic architectures, value-based algorithms like Q-learning and DQN, and policy-based techniques that directly optimize an agent's action-selection strategy. The curriculum extends beyond these core topics to include imitation learning, multi-agent training, and methods for handling continuous action spaces. Content is organized as markdown-driven documentation that generates static, navig

This project serves as an educational resource and training framework for developing intelligent agents through deep reinforcement learning. It provides a collection of practical tutorials and code examples designed to teach the implementation of neural networks for solving complex decision-making tasks. By focusing on hands-on learning, the material guides users through the process of building autonomous systems that improve their performance through trial and error. The framework centers on the integration of standardized simulation environments, allowing agents to interact with diverse tas

This project is a reinforcement learning framework and game AI engine designed for training adversarial agents in two-player turn-based games. It implements a training loop that utilizes self-play and Monte Carlo Tree Search to produce neural networks capable of predicting board strength and move probabilities. The system decouples the reinforcement learning engine from specific game rules through an abstract game logic interface, allowing for the definition of custom game rules, win conditions, and board representations. It supports integration with various deep learning frameworks to serve

AReaL is a system for agent orchestration, distributed model training, and parameter-efficient tuning. It provides a framework for developing multi-turn reasoning agents and training large models using reinforcement learning from human feedback. The project implements a toolkit for improving the visual reasoning and geometry problem solving capabilities of vision-language models. It utilizes a memory-efficient tuning system to optimize mathematical and reasoning models across different inference backends. The infrastructure supports large-scale training through tensor, pipeline, and expert p

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

OpenRLHF is a training framework and alignment library designed for reinforcement learning from human feedback across distributed GPU clusters. It provides tools for aligning large language models and multimodal vision-language models using algorithms such as PPO, GRPO, and DPO. The framework distinguishes itself through a distributed inference engine that overlaps sample rollout with training to increase throughput. It supports scaling to models exceeding 70 billion parameters via parameter sharding and handles long-context sequences through ring-attention sequence parallelism. The project

verl is a distributed training system designed for large language model alignment and reinforcement learning. It provides a framework for executing post-training pipelines, including supervised fine-tuning and reinforcement learning from human feedback, to refine model behavior and agentic capabilities. The system utilizes a hybrid training and inference engine that optimizes memory and communication when switching between model generation and gradient updates. It supports multi-modal reinforcement learning for models processing both image and text data, and implements algorithms such as PPO

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

Gymnasium is a suite of standardized APIs and simulation toolkits used to evaluate agent behavior and benchmark reinforcement learning algorithms. It provides a standardized interface for creating and interacting with simulated environments, enabling the training of reinforcement learning agents through a consistent set of interaction protocols. The project emphasizes experimental reproducibility through a versioned API and a system for tracking changes to environment logic using version suffixes. This ensures that learning results remain consistent and can be replicated across different soft

Modularized Implementation of Deep RL Algorithms in PyTorch

🕹️ A diverse suite of scalable reinforcement learning environments in JAX

Minigo is a TensorFlow-based reinforcement learning engine designed to master the game of Go. It functions as a comprehensive system for training neural networks to predict board policies and game outcomes, utilizing a model trainer to generate self-play data and optimize weights. The project is distinguished by its ability to perform large-scale game simulations using Kubernetes to distribute worker nodes across CPU, GPU, and TPU hardware. It employs a Monte Carlo Tree Search implementation to identify optimal moves and supports specialized hardware acceleration, including inference on Edge

This project is a comprehensive deep reinforcement learning course and training platform. It provides a structured educational curriculum that combines theoretical lessons with hands-on tutorials to teach the implementation of neural networks and agent behavior. The platform integrates a model sharing hub where users can upload, download, and version trained machine learning models. It also features a benchmarking system that uses leaderboards to evaluate and compare agent performance against community standards. The educational experience is delivered through interactive notebooks and inclu

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

Tensorpack is a high-level TensorFlow neural network framework and research library designed for building and training deep learning models. It provides a collection of reproducible neural network architectures for computer vision, generative tasks, reinforcement learning, and natural language processing. The project distinguishes itself through a specialized deep learning data pipeline that uses pure Python for parallel data loading and streaming. It includes a multi-GPU training orchestrator for distributing workloads via data-parallel strategies and a dedicated interpretability toolkit for