Farama-Foundation / GymnasiumView external linksLinks
An API standard for single-agent reinforcement learning environments, with popular reference environments and related utilities (formerly Gym)
☆11,326Updated this week
Alternatives and similar repositories for Gymnasium
Users that are interested in Gymnasium are comparing it to the libraries listed below
Sorting:
- PyTorch version of Stable Baselines, reliable implementations of reinforcement learning algorithms.☆12,745Feb 8, 2026Updated last week
- A toolkit for developing and comparing reinforcement learning algorithms.☆37,030Oct 11, 2024Updated last year
- High-quality single file implementation of Deep Reinforcement Learning algorithms with research-friendly features (PPO, DQN, C51, DDPG, T…☆9,097Jul 8, 2025Updated 7 months ago
- An API standard for multi-agent reinforcement learning environments, with popular reference environments and related utilities☆3,303Feb 6, 2026Updated last week
- A training framework for Stable Baselines3 reinforcement learning agents, with hyperparameter optimization and pre-trained agents include…☆2,723Updated this week
- A modular, primitive-first, python-first PyTorch library for Reinforcement Learning.☆3,300Updated this week
- Multi-Joint dynamics with Contact. A general purpose physics simulator.☆11,958Feb 9, 2026Updated last week
- A collection of robotics simulation environments for reinforcement learning☆848Jan 24, 2026Updated 3 weeks ago
- Ray is an AI compute engine. Ray consists of a core distributed runtime and a set of AI Libraries for accelerating ML workloads.☆41,259Updated this week
- An educational resource to help anyone learn deep reinforcement learning.☆11,588Aug 5, 2024Updated last year
- Composable transformations of Python+NumPy programs: differentiate, vectorize, JIT to GPU/TPU, and more☆34,848Updated this week
- An elegant PyTorch deep reinforcement learning library.☆10,198Dec 1, 2025Updated 2 months ago
- Train transformer language models with reinforcement learning.☆17,360Updated this week
- OpenAI Baselines: high-quality implementations of reinforcement learning algorithms☆16,651Aug 1, 2024Updated last year
- Unified framework for robot learning built on NVIDIA Isaac Sim☆6,337Updated this week
- Isaac Gym Reinforcement Learning Environments☆2,838Oct 26, 2024Updated last year
- Massively parallel rigidbody physics simulation on accelerator hardware.☆3,058Updated this week
- A collection of high-quality models for the MuJoCo physics engine, curated by Google DeepMind.☆3,036Jan 11, 2026Updated last month
- DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective.☆41,627Updated this week
- SBX: Stable Baselines Jax (SB3 + Jax) RL algorithms☆560Updated this week
- 🤗 Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal model…☆156,440Updated this week
- A high-throughput and memory-efficient inference and serving engine for LLMs☆70,205Updated this week
- Fast and memory-efficient exact attention☆22,231Updated this week
- Contrib package for Stable-Baselines3 - Experimental reinforcement learning (RL) code☆690Feb 6, 2026Updated last week
- A standard format for offline reinforcement learning datasets, with popular reference datasets and related utilities☆492Jan 10, 2026Updated last month
- 🤗 LeRobot: Making AI for Robotics more accessible with end-to-end learning☆21,583Updated this week
- Simple and easily configurable grid world environments for reinforcement learning☆2,398Dec 15, 2025Updated 2 months ago
- Google DeepMind's software stack for physics-based simulation and Reinforcement Learning environments, using MuJoCo.☆4,450Updated this week
- 🦜🔗 The platform for reliable agents.☆126,727Updated this week
- The simplest, fastest repository for training/finetuning medium-sized GPTs.☆52,955Nov 12, 2025Updated 3 months ago
- Pretrain, finetune ANY AI model of ANY size on 1 or 10,000+ GPUs with zero code changes.☆30,823Feb 4, 2026Updated last week
- Flax is a neural network library for JAX that is designed for flexibility.☆7,077Updated this week
- LlamaIndex is the leading framework for building LLM-powered agents over your data.☆46,977Updated this week
- Inference code for Llama models☆59,141Jan 26, 2025Updated last year
- LLM inference in C/C++☆94,823Updated this week
- Development repository for the Triton language and compiler☆18,429Updated this week
- A hyperparameter optimization framework☆13,515Updated this week
- A library of reinforcement learning components and agents☆3,918Feb 2, 2026Updated 2 weeks ago
- Tensors and Dynamic neural networks in Python with strong GPU acceleration☆97,298Updated this week