Open Source Reinforcement Learning Libraries
Sort By:
Reinforcement Learning Libraries
View 30 business solutionsBrowse free open source Reinforcement Learning Libraries and projects below. Use the toggles on the left to filter open source Reinforcement Learning Libraries by OS, license, language, programming language, and project status.
-
$300 Free Credits for Your Google Cloud ProjectsLaunch your next project with $300 in free Google Cloud credits—no strings attached. Test, build, and deploy without risk. Use your credits across the entire Google Cloud platform to find what works best for your needs. After your credits are used, continue with always-free tier services. Only pay when you're ready to scale. Sign up in minutes and start exploring.
-
Build Agents and Models on One PlatformGemini Enterprise Agent Platform is Google Cloud's comprehensive platform for developers to build, scale, govern, and optimize agents and models. Choose from Google's most advanced models and third-party models like Anthropic's Claude Model Family.
-
1
AirSim
A simulator for drones, cars and more, built on Unreal Engine
AirSim is an open-source, cross platform simulator for drones, cars and more vehicles, built on Unreal Engine with an experimental Unity release in the works. It supports software-in-the-loop simulation with popular flight controllers such as PX4 & ArduPilot and hardware-in-loop with PX4 for physically and visually realistic simulations. It is developed as an Unreal plugin that can simply be dropped into any Unreal environment. AirSim's development is oriented towards the goal of creating a platform for AI research to experiment with deep learning, computer vision and reinforcement learning algorithms for autonomous vehicles. For this purpose, AirSim also exposes APIs to retrieve data and control vehicles in a platform independent way. AirSim is fully enabled for multiple vehicles. This capability allows you to create multiple vehicles easily and use APIs to control them. -
2
TorchRL
A modular, primitive-first, python-first PyTorch library
TorchRL is an open-source Reinforcement Learning (RL) library for PyTorch. TorchRL provides PyTorch and python-first, low and high-level abstractions for RL that are intended to be efficient, modular, documented, and properly tested. The code is aimed at supporting research in RL. Most of it is written in Python in a highly modular way, such that researchers can easily swap components, transform them, or write new ones with little effort. -
3
EnvPool
C++-based high-performance parallel environment execution engine
EnvPool is a fast, asynchronous, and parallel RL environment library designed for scaling reinforcement learning experiments. Developed by SAIL at Singapore, it leverages C++ backend and Python frontend for extremely high-speed environment interaction, supporting thousands of environments running in parallel on a single machine. It's compatible with Gymnasium API and RLlib, making it suitable for scalable training pipelines. -
4
Bullet Physics SDK
Real-time collision detection and multi-physics simulation for VR
This is the official C++ source code repository of the Bullet Physics SDK: real-time collision detection and multi-physics simulation for VR, games, visual effects, robotics, machine learning etc. We are developing a new differentiable simulator for robotics learning, called Tiny Differentiable Simulator, or TDS. The simulator allows for hybrid simulation with neural networks. It allows different automatic differentiation backends, for forward and reverse mode gradients. TDS can be trained using Deep Reinforcement Learning, or using Gradient based optimization (for example LFBGS). In addition, the simulator can be entirely run on CUDA for fast rollouts, in combination with Augmented Random Search. This allows for 1 million simulation steps per second. It is highly recommended to use PyBullet Python bindings for improved support for robotics, reinforcement learning and VR. Use pip install pybullet and checkout the PyBullet Quickstart Guide. -
Cut Data Warehouse Costs by 54%BigQuery delivers 54% lower TCO with exabyte scale and flexible pricing. Free migration tools handle the SQL translation automatically.
-
5
Weights and Biases
Tool for visualizing and tracking your machine learning experiments
Use W&B to build better models faster. Track and visualize all the pieces of your machine learning pipeline, from datasets to production models. Quickly identify model regressions. Use W&B to visualize results in real time, all in a central dashboard. Focus on the interesting ML. Spend less time manually tracking results in spreadsheets and text files. Capture dataset versions with W&B Artifacts to identify how changing data affects your resulting models. Reproduce any model, with saved code, hyperparameters, launch commands, input data, and resulting model weights. Set wandb.config once at the beginning of your script to save your hyperparameters, input settings (like dataset name or model type), and any other independent variables for your experiments. This is useful for analyzing your experiments and reproducing your work in the future. Setting configs also allows you to visualize the relationships between features of your model architecture or data pipeline and model performance. -
6
Alibi Explain
Algorithms for explaining machine learning models
Alibi is a Python library aimed at machine learning model inspection and interpretation. The focus of the library is to provide high-quality implementations of black-box, white-box, local and global explanation methods for classification and regression models. -
7
Deep Reinforcement Learning for Keras
Deep Reinforcement Learning for Keras.
keras-rl implements some state-of-the-art deep reinforcement learning algorithms in Python and seamlessly integrates with the deep learning library Keras. Furthermore, keras-rl works with OpenAI Gym out of the box. This means that evaluating and playing around with different algorithms is easy. Of course, you can extend keras-rl according to your own needs. You can use built-in Keras callbacks and metrics or define your own. Even more so, it is easy to implement your own environments and even algorithms by simply extending some simple abstract classes. Documentation is available online. -
8
Multi-Agent Orchestrator
Flexible and powerful framework for managing multiple AI agents
Multi-Agent Orchestrator is an AI coordination framework that enables multiple intelligent agents to work together to complete complex, multi-step workflows. -
9
TensorHouse
A collection of reference Jupyter notebooks and demo AI/ML application
TensorHouse is a scalable reinforcement learning (RL) platform that focuses on high-throughput experience generation and distributed training. It is designed to efficiently train agents across multiple environments and compute resources. TensorHouse enables flexible experiment management, making it suitable for large-scale RL experiments in both research and applied settings. -
Go from Code to Production URL in SecondsSkip the Kubernetes configs. Cloud Run handles HTTPS, scaling, and infrastructure automatically. Two million requests free per month.
-
10
AgentUniverse
agentUniverse is a LLM multi-agent framework
AgentUniverse is a multi-agent AI framework that enables coordination between multiple intelligent agents for complex task execution and automation. -
11
CleanRL
High-quality single file implementation of Deep Reinforcement Learning
CleanRL is a Deep Reinforcement Learning library that provides high-quality single-file implementation with research-friendly features. The implementation is clean and simple, yet we can scale it to run thousands of experiments using AWS Batch. CleanRL is not a modular library and therefore it is not meant to be imported. At the cost of duplicate code, we make all implementation details of a DRL algorithm variant easy to understand, so CleanRL comes with its own pros and cons. You should consider using CleanRL if you want to 1) understand all implementation details of an algorithm's variant or 2) prototype advanced features that other modular DRL libraries do not support (CleanRL has minimal lines of code so it gives you great debugging experience and you don't have to do a lot of subclassing like sometimes in modular DRL libraries). -
12
Gym
Toolkit for developing and comparing reinforcement learning algorithms
Gym by OpenAI is a toolkit for developing and comparing reinforcement learning algorithms. It supports teaching agents, everything from walking to playing games like Pong or Pinball. Open source interface to reinforce learning tasks. The gym library provides an easy-to-use suite of reinforcement learning tasks. Gym provides the environment, you provide the algorithm. You can write your agent using your existing numerical computation library, such as TensorFlow or Theano. It makes no assumptions about the structure of your agent, and is compatible with any numerical computation library, such as TensorFlow or Theano. The gym library is a collection of test problems — environments — that you can use to work out your reinforcement learning algorithms. These environments have a shared interface, allowing you to write general algorithms. -
13
Gymnasium
An API standard for single-agent reinforcement learning environments
Gymnasium is a fork of OpenAI Gym, maintained by the Farama Foundation, that provides a standardized API for reinforcement learning environments. It improves upon Gym with better support, maintenance, and additional features while maintaining backward compatibility. -
14
BindsNET
Simulation of spiking neural networks (SNNs) using PyTorch
A Python package used for simulating spiking neural networks (SNNs) on CPUs or GPUs using PyTorch Tensor functionality. BindsNET is a spiking neural network simulation library geared towards the development of biologically inspired algorithms for machine learning. This package is used as part of ongoing research on applying SNNs to machine learning (ML) and reinforcement learning (RL) problems in the Biologically Inspired Neural & Dynamical Systems (BINDS) lab. -
15
Machine Learning PyTorch Scikit-Learn
Code Repository for Machine Learning with PyTorch and Scikit-Learn
Initially, this project started as the 4th edition of Python Machine Learning. However, after putting so much passion and hard work into the changes and new topics, we thought it deserved a new title. So, what’s new? There are many contents and additions, including the switch from TensorFlow to PyTorch, new chapters on graph neural networks and transformers, a new section on gradient boosting, and many more that I will detail in a separate blog post. For those who are interested in knowing what this book covers in general, I’d describe it as a comprehensive resource on the fundamental concepts of machine learning and deep learning. The first half of the book introduces readers to machine learning using scikit-learn, the defacto approach for working with tabular datasets. Then, the second half of this book focuses on deep learning, including applications to natural language processing and computer vision. -
16
Ray
A unified framework for scalable computing
Modern workloads like deep learning and hyperparameter tuning are compute-intensive and require distributed or parallel execution. Ray makes it effortless to parallelize single machine code — go from a single CPU to multi-core, multi-GPU or multi-node with minimal code changes. Accelerate your PyTorch and Tensorflow workload with a more resource-efficient and flexible distributed execution framework powered by Ray. Accelerate your hyperparameter search workloads with Ray Tune. Find the best model and reduce training costs by using the latest optimization algorithms. Deploy your machine learning models at scale with Ray Serve, a Python-first and framework agnostic model serving framework. Scale reinforcement learning (RL) with RLlib, a framework-agnostic RL library that ships with 30+ cutting-edge RL algorithms including A3C, DQN, and PPO. Easily build out scalable, distributed systems in Python with simple and composable primitives in Ray Core. -
17
Stable Baselines3
PyTorch version of Stable Baselines
Stable Baselines3 (SB3) is a set of reliable implementations of reinforcement learning algorithms in PyTorch. It is the next major version of Stable Baselines. You can read a detailed presentation of Stable Baselines3 in the v1.0 blog post or our JMLR paper. These algorithms will make it easier for the research community and industry to replicate, refine, and identify new ideas, and will create good baselines to build projects on top of. We expect these tools will be used as a base around which new ideas can be added, and as a tool for comparing a new approach against existing ones. We also hope that the simplicity of these tools will allow beginners to experiment with a more advanced toolset, without being buried in implementation details. -
18
AndroidEnv
RL research on Android devices
android_env is a reinforcement learning (RL) environment developed by Google DeepMind that enables agents to interact with Android applications directly as a learning environment. It provides a standardized API for training agents to perform tasks on Android apps, supporting tasks ranging from games to productivity apps, making it suitable for research in real-world RL settings. -
19
H2O LLM Studio
Framework and no-code GUI for fine-tuning LLMs
Welcome to H2O LLM Studio, a framework and no-code GUI designed for fine-tuning state-of-the-art large language models (LLMs). You can also use H2O LLM Studio with the command line interface (CLI) and specify the configuration file that contains all the experiment parameters. To finetune using H2O LLM Studio with CLI, activate the pipenv environment by running make shell. With H2O LLM Studio, training your large language model is easy and intuitive. First, upload your dataset and then start training your model. Start by creating an experiment. You can then monitor and manage your experiment, compare experiments, or push the model to Hugging Face to share it with the community. -
20
Habitat-Lab
A modular high-level library to train embodied AI agents
Habitat-Lab is a modular high-level library for end-to-end development in embodied AI. It is designed to train agents to perform a wide variety of embodied AI tasks in indoor environments, as well as develop agents that can interact with humans in performing these tasks. Allowing users to train agents in a wide variety of single and multi-agent tasks (e.g. navigation, rearrangement, instruction following, question answering, human following), as well as define novel tasks. Configuring and instantiating a diverse set of embodied agents, including commercial robots and humanoids, specifying their sensors and capabilities. Providing algorithms for single and multi-agent training (via imitation or reinforcement learning, or no learning at all as in SensePlanAct pipelines), as well as tools to benchmark their performance on the defined tasks using standard metrics. -
21
ML for Trading
Code for machine learning for algorithmic trading, 2nd edition
On over 800 pages, this revised and expanded 2nd edition demonstrates how ML can add value to algorithmic trading through a broad range of applications. Organized in four parts and 24 chapters, it covers the end-to-end workflow from data sourcing and model development to strategy backtesting and evaluation. Covers key aspects of data sourcing, financial feature engineering, and portfolio management. The design and evaluation of long-short strategies based on a broad range of ML algorithms, how to extract tradeable signals from financial text data like SEC filings, earnings call transcripts or financial news. Using deep learning models like CNN and RNN with financial and alternative data, and how to generate synthetic data with Generative Adversarial Networks, as well as training a trading agent using deep reinforcement learning. -
22
MedicalGPT
MedicalGPT: Training Your Own Medical GPT Model with ChatGPT Training
MedicalGPT training medical GPT model with ChatGPT training pipeline, implementation of Pretraining, Supervised Finetuning, Reward Modeling and Reinforcement Learning. MedicalGPT trains large medical models, including secondary pre-training, supervised fine-tuning, reward modeling, and reinforcement learning training. -
23
Project Malmo
A platform for Artificial Intelligence experimentation on Minecraft
How can we develop artificial intelligence that learns to make sense of complex environments? That learns from others, including humans, how to interact with the world? That learns transferable skills throughout its existence, and applies them to solve new, challenging problems? Project Malmo sets out to address these core research challenges, addressing them by integrating (deep) reinforcement learning, cognitive science, and many ideas from artificial intelligence. The Malmo platform is a sophisticated AI experimentation platform built on top of Minecraft, and designed to support fundamental research in artificial intelligence. The Project Malmo platform consists of a mod for the Java version, and code that helps artificial intelligence agents sense and act within the Minecraft environment. The two components can run on Windows, Linux, or Mac OS, and researchers can program their agents in any programming language they’re comfortable with. -
24
ReinforcementLearningAnIntroduction.jl
Julia code for the book Reinforcement Learning An Introduction
This project provides the Julia code to generate figures in the book Reinforcement Learning: An Introduction(2nd). One of our main goals is to help users understand the basic concepts of reinforcement learning from an engineer's perspective. Once you have grasped how different components are organized, you're ready to explore a wide variety of modern deep reinforcement learning algorithms in ReinforcementLearningZoo.jl. -
25
Transformer Reinforcement Learning X
A repo for distributed training of language models with Reinforcement
trlX is a distributed training framework designed from the ground up to focus on fine-tuning large language models with reinforcement learning using either a provided reward function or a reward-labeled dataset. Training support for Hugging Face models is provided by Accelerate-backed trainers, allowing users to fine-tune causal and T5-based language models of up to 20B parameters, such as facebook/opt-6.7b, EleutherAI/gpt-neox-20b, and google/flan-t5-xxl. For models beyond 20B parameters, trlX provides NVIDIA NeMo-backed trainers that leverage efficient parallelism techniques to scale effectively.
Guide to Open Source Reinforcement Learning Libraries
Open source reinforcement learning libraries provide developers, researchers, and organizations with frameworks for building, training, evaluating, and deploying reinforcement learning models. These libraries simplify the process of creating agents that learn by interacting with environments and improving their decision-making through trial and error. By offering reusable components, standardized workflows, and extensive documentation, they reduce development effort while supporting experimentation across a wide range of learning tasks. Many libraries also support integration with machine learning frameworks, simulation environments, and cloud infrastructure to streamline development.
These libraries are widely used in fields such as robotics, autonomous systems, gaming, finance, manufacturing, and scientific research. They often include tools for implementing popular reinforcement learning algorithms, managing training pipelines, tracking performance metrics, and comparing different approaches under consistent conditions. Many also provide utilities for distributed training, hyperparameter optimization, environment customization, and visualization, making it easier to scale projects from early prototypes to larger production workloads. Their flexibility allows teams to adapt models for unique business objectives and operational requirements.
As reinforcement learning continues to evolve, open source libraries remain central to advancing innovation and collaboration. Organizations can customize existing capabilities, contribute improvements, and adopt emerging techniques without being limited by proprietary ecosystems. This collaborative development model encourages continuous enhancements, broader compatibility, and faster adoption of new research. Whether supporting academic exploration or commercial initiatives, open source reinforcement learning libraries help organizations accelerate development while maintaining control over their workflows and technology choices.
Open Source Reinforcement Learning Libraries Features
- Flexible training pipelines: Support configurable workflows for training, evaluation, and policy improvement across reinforcement learning tasks.
- Multiple algorithm support: Include value-based, policy-based, and actor-critic methods for solving diverse decision-making challenges.
- Environment compatibility: Connect with standardized simulation environments for consistent testing and benchmarking.
- Custom environment creation: Enable users to build specialized environments matching unique business or research objectives.
- Model checkpointing: Save training progress regularly for recovery, comparison, and continued optimization.
- Hyperparameter configuration: Allow adjustment of learning rates, batch sizes, exploration settings, and other training variables.
- Performance monitoring: Track rewards, losses, and learning metrics throughout training to measure improvement.
- Hardware acceleration: Utilize GPUs and other supported processors to reduce training time for computationally intensive workloads.
What Are the Different Types of Open Source Reinforcement Learning Libraries?
- Model-free libraries: Learn effective policies through trial and error without requiring environment models.
- Model-based libraries: Build environment representations to improve planning, prediction, and decision-making efficiency.
- Deep reinforcement learning libraries: Combine neural networks with reinforcement learning techniques for complex learning tasks.
- Multi-agent reinforcement learning libraries: Support environments where multiple agents cooperate, compete, or interact simultaneously.
- Offline reinforcement learning libraries: Train models using previously collected datasets instead of continuous environment interaction.
- Distributed reinforcement learning libraries: Scale training across multiple devices to reduce processing time and improve performance.
- Research-focused libraries: Prioritize experimentation, algorithm development, benchmarking, and academic exploration with flexible architectures.
- Production-ready libraries: Emphasize reliability, deployment support, monitoring capabilities, and integration with enterprise workflows.
Benefits of Open Source Reinforcement Learning Libraries
- Greater flexibility: Modify algorithms and workflows to match unique research or business objectives.
- Lower licensing costs: Reduce upfront expenses while expanding experimentation opportunities.
- Transparent development: Review implementation details to improve trust and understanding.
- Community contributions: Benefit from continuous enhancements, bug fixes, and shared knowledge.
- Broad customization: Adapt training methods, environments, and evaluation processes with fewer restrictions.
- Faster innovation: Access emerging reinforcement learning techniques through active development communities.
- Better interoperability: Connect with complementary machine learning, analytics, and infrastructure tools.
- Scalable deployment: Support projects ranging from prototypes to large production environments.
What Types of Users Use Open Source Reinforcement Learning Libraries?
- AI researchers: Build, evaluate, and refine reinforcement learning models for academic and experimental work.
- Data science teams: Explore decision-making methods using reinforcement learning tools across research initiatives.
- Robotics engineers: Train autonomous systems to improve actions through continuous environmental feedback.
- Machine learning engineers: Develop and optimize reinforcement learning workflows for production-ready AI applications.
- Universities: Teach reinforcement learning concepts through practical projects and laboratory exercises.
- Research laboratories: Test new algorithms, environments, and training approaches for advanced AI studies.
- Autonomous vehicle developers: Improve driving strategies by training agents under simulated conditions.
- Industrial automation teams: Optimize operational decisions using reinforcement learning techniques across complex processes.
How Much Do Open Source Reinforcement Learning Libraries Cost?
The cost of open source reinforcement learning libraries can vary widely depending on how they are implemented and supported within an organization. While the libraries themselves are often available without licensing fees, businesses should still account for expenses related to deployment, infrastructure, customization, and ongoing maintenance. Small teams may be able to use existing resources to build and test reinforcement learning models, while larger organizations often invest in more powerful computing environments and specialized expertise to support production workloads.
Additional costs may include cloud computing resources, data storage, model training, consulting services, employee training, and integration with existing tools. Organizations with advanced performance, security, or scalability requirements may also spend more on infrastructure and operational support. Evaluating the total cost of ownership rather than focusing only on acquisition costs provides a more accurate understanding of the investment required for open source reinforcement learning libraries.
What Software Can Integrate With Open Source Reinforcement Learning Libraries?
Open source reinforcement learning libraries can integrate with machine learning frameworks, allowing teams to build, train, and evaluate reinforcement learning models alongside other artificial intelligence workflows. They also connect with simulation platforms that create virtual environments for testing agents before deployment in real-world scenarios. Data storage solutions support logging, dataset management, and experiment tracking, while visualization and analytics tools help monitor training progress and evaluate performance over time.
Cloud infrastructure platforms can provide scalable computing resources for training complex models, and containerization tools simplify deployment across development and production environments. Integration with robotics platforms, game engines, and automation frameworks enables reinforcement learning agents to interact with physical devices or simulated systems. Version control, workflow automation, and monitoring tools also complement these libraries by supporting collaboration, reproducibility, and operational management throughout the development lifecycle.
Recent Trends Related to Open Source Reinforcement Learning Libraries
- More libraries emphasize scalable distributed training to support larger experiments across multiple devices and cloud environments.
- Offline reinforcement learning receives greater attention, allowing models to learn from existing datasets instead of continuous live interactions.
- Improved simulation compatibility helps researchers evaluate learning strategies before deploying them in physical or production environments.
- Better support for large language model integration expands reinforcement learning into conversational and reasoning-focused applications.
- More developers prioritize modular architectures that simplify customization, testing, and maintenance across different reinforcement learning workflows.
- Growing demand for reproducible experiments encourages standardized benchmarks, evaluation methods, and documentation across open source communities.
- Hardware acceleration improvements reduce training time while making advanced reinforcement learning workflows more accessible for broader audiences.
- Expanded multi-agent capabilities support complex environments where multiple learning agents cooperate or compete to solve challenging tasks.
How To Get Started With Open Source Reinforcement Learning Libraries
Selecting the right open source reinforcement learning libraries starts with defining your objectives, whether they involve research, education, simulation, or production deployment. Evaluate whether the library supports the algorithms, environments, and workflows your team requires. Consider compatibility with existing machine learning frameworks, hardware acceleration, and operating environments to reduce integration challenges.
Review the quality of documentation, tutorials, and technical references to determine how quickly users can become productive. Active development, frequent updates, and a strong contributor community are good indicators that the library will continue to improve over time. Assess scalability, customization options, and performance using workloads similar to your intended use case. Finally, examine licensing terms, security practices, and long-term maintenance to ensure the library aligns with organizational policies and future growth plans.