Open Source Python Reinforcement Learning Frameworks
Sort By:
Python Reinforcement Learning Frameworks
View 27 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.
-
99.99% Uptime for MySQL and PostgreSQL on Google CloudCloud SQL Enterprise Plus gives you a 99.99% availability SLA with near-zero downtime maintenance—typically under 10 seconds. Get 2x better read/write performance, intelligent data caching, and 35 days of point-in-time recovery. Supports MySQL, PostgreSQL, and SQL Server with built-in vector search for gen AI apps. New customers get $300 in free credit.
-
Build on Google Cloud with $300 in Free CreditStart your next project with $300 in free Google Cloud credit. Spin up VMs, run containers, query exabytes in BigQuery, or build AI apps with Vertex AI and Gemini. Once your credits are used, keep building with 20+ products with free monthly usage, including Compute Engine, Cloud Storage, GKE, and Cloud Run functions. Sign up to start building right away.
-
1
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. -
2
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. -
3
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. -
4
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. -
Build AI Apps with Gemini 3 on Vertex AIVertex AI gives developers access to Gemini 3—Google’s most advanced reasoning and coding model—plus 200+ foundation models including Claude, Llama, and Gemma. Build generative AI apps with Vertex AI Studio, customize with fine-tuning, and deploy to production with enterprise-grade MLOps. New customers get $300 in free credits.
-
5
CCZero (中国象棋Zero)
Implement AlphaZero/AlphaGo Zero methods on Chinese chess
ChineseChess-AlphaZero is a project that implements the AlphaZero algorithm for the game of Chinese Chess (Xiangqi). It adapts DeepMind’s AlphaZero method—combining neural networks and Monte Carlo Tree Search (MCTS)—to learn and play Chinese Chess without prior human data. The system includes self-play, training, and evaluation pipelines tailored to Xiangqi's unique game mechanics. -
6
DouZero
[ICML 2021] DouZero: Mastering DouDizhu
DouZero is a reinforcement learning-based AI for playing DouDizhu, a popular Chinese card game. It focuses on perfecting AI strategies for competitive play using value-based deep RL techniques. -
7
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. -
8
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. -
9
PyBoy
Game Boy emulator written in Python
It is highly recommended to read the report to get a light introduction to Game Boy emulation. But do be aware, that the Python implementation has changed a lot. The report is relevant, even though you want to contribute to another emulator or create your own. If you are looking to make a bot or AI, you can find all the external components in the PyBoy Documentation. There is also a short example on our Wiki page Scripts, AI and Bots as well as in the examples directory. If more features are needed, or if you find a bug, don't hesitate to make an issue here on GitHub, or write on our Discord channel. If you need more details, or if you need to compile from source, check out the detailed installation instructions. We support: macOS, Raspberry Pi (Raspbian), Linux (Ubuntu), and Windows 10. -
Cut Cloud Costs with Google Compute EngineSave on compute costs with Compute Engine. Reduce your batch jobs and workload bill 60-91% with Spot VMs. Compute Engine's committed use offers customers up to 70% savings through sustained use discounts. Plus, you get one free e2-micro VM monthly and $300 credit to start.
-
10
WikiSQL
A large annotated semantic parsing corpus for developing NL interfaces
A large crowd-sourced dataset for developing natural language interfaces for relational databases. WikiSQL is the dataset released along with our work Seq2SQL: Generating Structured Queries from Natural Language using Reinforcement Learning. Regarding tokenization and Stanza, when WikiSQL was written 3-years ago, it relied on Stanza, a CoreNLP python wrapper that has since been deprecated. If you'd still like to use the tokenizer, please use the docker image. We do not anticipate switching to the current Stanza as changes to the tokenizer would render the previous results not reproducible. -
11
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. -
12
Best-of Machine Learning with Python
A ranked list of awesome machine learning Python libraries
This curated list contains 900 awesome open-source projects with a total of 3.3M stars grouped into 34 categories. All projects are ranked by a project-quality score, which is calculated based on various metrics automatically collected from GitHub and different package managers. If you like to add or update projects, feel free to open an issue, submit a pull request, or directly edit the projects.yaml. Contributions are very welcome! General-purpose machine learning and deep learning frameworks. -
13
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). -
14
Jittor
Jittor is a high-performance deep learning framework
Jittor is a high-performance deep learning framework based on JIT compiling and meta-operators. The whole framework and meta-operators are compiled just in time. A powerful op compiler and tuner are integrated into Jittor. It allowed us to generate high-performance code specialized for your model. Jittor also contains a wealth of high-performance model libraries, including image recognition, detection, segmentation, generation, differentiable rendering, geometric learning, reinforcement learning, etc. The front-end language is Python. Module Design and Dynamic Graph Execution is used in the front-end, which is the most popular design for deep learning framework interface. The back-end is implemented by high-performance languages, such as CUDA, C++. Jittor'op is similar to NumPy. Let's try some operations. We create Var a and b via operation jt.float32, and add them. Printing those variables shows they have the same shape and dtype. -
15
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. -
16
SMAC
SMAC: The StarCraft Multi-Agent Challenge
SMAC (StarCraft II Multi-Agent Challenge) is a benchmark environment for cooperative multi-agent reinforcement learning (MARL), based on real-time strategy (RTS) game scenarios in StarCraft II. It allows researchers to test algorithms where multiple units (agents) must collaborate to win battles against built-in game AI opponents. SMAC provides a controlled testbed for studying decentralized execution and centralized training paradigms in MARL. -
17
Tensorforce
A TensorFlow library for applied reinforcement learning
Tensorforce is an open-source deep reinforcement learning framework built on TensorFlow, emphasizing modularized design and straightforward usability for applied research and practice. -
18
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. -
19
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. -
20
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. -
21
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. -
22
Google Research Football
Check out the new game server
Google Research Football is a reinforcement learning environment simulating soccer matches. It focuses on learning complex behaviors such as team collaboration and strategy formation in competitive settings. -
23
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. -
24
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. -
25
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.
