Open Source Python Reinforcement Learning Frameworks
Sort By:
Python Reinforcement Learning Frameworks
View 28 business solutionsBrowse free open source Python Reinforcement Learning Frameworks and projects below. Use the toggles on the left to filter open source Python Reinforcement Learning Frameworks by OS, license, language, programming language, and project status.
-
The Apple Device Management and Security PlatformAchieve harmony across your Apple device fleet with Kandji's unmatched management and security capabilities.
-
No-Nonsense Code-to-Cloud Security for Devs | AikidoAikido provides a unified security platform for developers, combining 12 powerful scans like SAST, DAST, and CSPM. AI-driven AutoFix and AutoTriage streamline vulnerability management, while runtime protection blocks attacks.
-
1
DeepSeek-V3
Powerful AI language model (MoE) optimized for efficiency/performance
DeepSeek-V3 is a robust Mixture-of-Experts (MoE) language model developed by DeepSeek, featuring a total of 671 billion parameters, with 37 billion activated per token. It employs Multi-head Latent Attention (MLA) and the DeepSeekMoE architecture to enhance computational efficiency. The model introduces an auxiliary-loss-free load balancing strategy and a multi-token prediction training objective to boost performance. Trained on 14.8 trillion diverse, high-quality tokens, DeepSeek-V3 underwent supervised fine-tuning and reinforcement learning to fully realize its capabilities. Evaluations indicate that it outperforms other open-source models and rivals leading closed-source models, achieving this with a training duration of 55 days on 2,048 Nvidia H800 GPUs, costing approximately $5.58 million. -
2
DeepSeek R1
Open-source, high-performance AI model with advanced reasoning
DeepSeek-R1 is an open-source large language model developed by DeepSeek, designed to excel in complex reasoning tasks across domains such as mathematics, coding, and language. DeepSeek R1 offers unrestricted access for both commercial and academic use. The model employs a Mixture of Experts (MoE) architecture, comprising 671 billion total parameters with 37 billion active parameters per token, and supports a context length of up to 128,000 tokens. DeepSeek-R1's training regimen uniquely integrates large-scale reinforcement learning (RL) without relying on supervised fine-tuning, enabling the model to develop advanced reasoning capabilities. This approach has resulted in performance comparable to leading models like OpenAI's o1, while maintaining cost-efficiency. To further support the research community, DeepSeek has released distilled versions of the model based on architectures such as LLaMA and Qwen. -
3
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. -
4
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. -
QA Wolf | We Write, Run and Maintain TestsQA Wolf is an AI-native service that delivers 80% automated E2E test coverage for web & mobile apps in weeks not years.
-
5
LightZero
[NeurIPS 2023 Spotlight] LightZero
LightZero is an efficient, scalable, and open-source framework implementing MuZero, a powerful model-based reinforcement learning algorithm that learns to predict rewards and transitions without explicit environment models. Developed by OpenDILab, LightZero focuses on providing a highly optimized and user-friendly platform for both academic research and industrial applications of MuZero and similar algorithms. -
6
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. -
7
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. -
8
OpenRLHF
An Easy-to-use, Scalable and High-performance RLHF Framework
OpenRLHF is an easy-to-use, scalable, and high-performance framework for Reinforcement Learning with Human Feedback (RLHF). It supports various training techniques and model architectures. -
9
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. -
Power through agendas and documents, make more informed decisions and conduct board meetings faster.iBabs not only captures the entire decision-making process – it takes all the paperwork out of meetings. iBabs empowers everyone who has ever organized or attended, a meeting. With a seemingly simple app that offers complete control and a comprehensive overview of all those fiddly details. With about 3000 organizations and over 300,000 users, iBabs gives you peace of mind. So you can quickly organize effective meetings, and good decisions can be made with confidence. iBabs didn’t just happen overnight. We started analyzing and simplifying board meeting processes many years ago. We understand all the work that goes into meetings, and how to streamline everything so it all flows smoothly. On any device, confidentially, securely and automatically. Make good decisions with confidence.
-
10
Agent S
Agent S: an open agentic framework that uses computers like a human
Agent S is an open-source agentic framework designed to enable autonomous computer use through an Agent-Computer Interface (ACI). Built to operate graphical user interfaces like a human, it allows AI agents to perceive screens, reason about tasks, and execute actions across macOS, Windows, and Linux systems. The latest version, Agent S3, surpasses human-level performance on the OSWorld benchmark, demonstrating state-of-the-art results in complex multi-step computer tasks. Agent S combines powerful foundation models (such as GPT-5) with grounding models like UI-TARS to translate visual inputs into precise executable actions. It supports flexible deployment via CLI, SDK, or cloud, and integrates with multiple model providers including OpenAI, Anthropic, Gemini, Azure, and Hugging Face endpoints. With optional local code execution, reflection mechanisms, and compositional planning, Agent S provides a scalable and research-driven framework for building advanced computer-use agents. -
11
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. -
12
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. -
13
dm_control
DeepMind's software stack for physics-based simulation
DeepMind's software stack for physics-based simulation and Reinforcement Learning environments, using MuJoCo. DeepMind's software stack for physics-based simulation and Reinforcement Learning environments, using MuJoCo physics. The MuJoCo Python bindings support three different OpenGL rendering backends: EGL (headless, hardware-accelerated), GLFW (windowed, hardware-accelerated), and OSMesa (purely software-based). At least one of these three backends must be available in order render through dm_control. Hardware rendering with a windowing system is supported via GLFW and GLEW. On Linux these can be installed using your distribution's package manager. "Headless" hardware rendering (i.e. without a windowing system such as X11) requires EXT_platform_device support in the EGL driver. While dm_control has been largely updated to use the pybind11-based bindings provided via the mujoco package, at this time it still relies on some legacy components that are automatically generated. -
14
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. -
15
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. -
16
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. -
17
AnyTrading
The most simple, flexible, and comprehensive OpenAI Gym trading
gym-anytrading is an OpenAI Gym-compatible environment designed for developing and testing reinforcement learning algorithms on trading strategies. It simulates trading environments for financial markets, including stocks and forex. -
18
Brax
Massively parallel rigidbody physics simulation
Brax is a fast and fully differentiable physics engine for large-scale rigid body simulations, built on JAX. It is designed for research in reinforcement learning and robotics, enabling efficient simulations and gradient-based optimization. -
19
ManiSkill
SAPIEN Manipulation Skill Framework
ManiSkill is a benchmark platform for training and evaluating reinforcement learning agents on dexterous manipulation tasks using physics-based simulations. Developed by Hao Su Lab, it focuses on robotic manipulation with diverse, high-quality 3D tasks designed to challenge perception, control, and planning in robotics. ManiSkill provides both low-level control and visual observation spaces for realistic learning scenarios. -
20
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. -
21
TextWorld
TextWorld is a sandbox learning environment for the training
TextWorld is a learning environment designed to train reinforcement learning agents to play text-based games, where actions and observations are entirely in natural language. Developed by Microsoft Research, TextWorld focuses on language understanding, planning, and interaction in complex, narrative-driven environments. It generates games procedurally, enabling scalable testing of agents’ natural language processing and decision-making abilities. -
22
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. -
23
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. -
24
VectorizedMultiAgentSimulator (VMAS)
VMAS is a vectorized differentiable simulator
VectorizedMultiAgentSimulator is a high-performance, vectorized simulator for multi-agent systems, focusing on large-scale agent interactions in shared environments. It is designed for research in multi-agent reinforcement learning, robotics, and autonomous systems where thousands of agents need to be simulated efficiently. -
25
robosuite
A Modular Simulation Framework and Benchmark for Robot Learning
Robosuite is a modular and extensible simulation framework for robotic manipulation tasks, built on top of MuJoCo. Developed by the ARISE Initiative, Robosuite offers a set of standardized benchmarks and customizable environments designed to advance research in robotic manipulation, control, and imitation learning. It emphasizes realistic simulations and ease of use for both single-task and multi-task learning.
