Reinforcement learning simulators

IsaacGymEnvs is a GPU-accelerated physics sandbox and robotics policy training suite designed for reinforcement learning. It serves as a vectorized robotic simulator that runs thousands of parallel environments on GPUs to accelerate the training of neural networks. The project provides a sim-to-real transfer framework that utilizes domain randomization and physics variations to ensure policies trained in simulation are robust enough for deployment on real hardware. It distinguishes itself through a high-performance architecture that uses tensor-based state management to handle observations an

Newton is a GPU-accelerated physics engine and robotics simulation platform designed for high-performance modeling of rigid bodies and complex articulations. It functions as a differentiable physics engine, calculating gradients to enable mathematical optimization and machine learning. The platform is distinguished by its ability to execute multiple parallel physics worlds on a single GPU, which accelerates data collection for reinforcement learning. It also supports the simulation of deformable bodies, such as cloth and cables, using particle-based methods and multi-physics coupling. Newton

The Arcade Learning Environment is a research-focused platform that provides a high-performance emulation engine for Atari 2600 games. It serves as a standardized environment for training and evaluating artificial intelligence agents, bridging native game execution with machine learning libraries through a dedicated Python interface. The project distinguishes itself by offering robust support for parallel and vectorized environment execution, allowing multiple game instances to run simultaneously to accelerate data collection. It includes specialized tools for asynchronous command queuing and

Gym is a reinforcement learning environment toolkit and agent simulation framework. It provides a standardized API and a universal communication interface that defines how learning agents interact with simulation environments through actions and observations. The project includes a benchmark environment suite and a diverse library of pre-configured simulation worlds, including physics engines and classic control tasks. It enables the creation of custom simulation environments to train agents in specific operational scenarios while ensuring reproducibility across different learning algorithms.

This project is a reinforcement learning toolkit and simulation-based AI trainer for creating intelligent agents within Unity simulations. It provides a multi-agent simulation framework for configuring cooperative or competitive scenarios and includes an environment wrapper that bridges simulations with standard machine learning libraries using gym-style interfaces. The system features a native cross-platform inference engine that executes trained neural network models for real-time decision making without external dependencies. It enables the acceleration of the learning process by running m

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

Osim-rl is a research environment designed for the development and evaluation of reinforcement learning agents within physics-based musculoskeletal simulations. It provides a standardized interface that maps physiological state observations to muscle excitation control signals, enabling the study of human movement and biomechanics through iterative policy optimization. The framework distinguishes itself by integrating high-fidelity musculoskeletal modeling with tools for scientific benchmarking and reproducible experimentation. It allows researchers to define custom reward functions and adjus

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

AirSim is a high-fidelity simulation platform designed for the development and testing of autonomous vehicles. Built as a plugin for game engines, it provides a physics-based environment that models vehicle dynamics and sensor data, serving as a foundation for robotics research, computer vision training, and reinforcement learning. The platform distinguishes itself through its support for hardware-in-the-loop and software-in-the-loop testing, allowing developers to validate control logic and firmware against real-world signals or concurrent processes. It offers extensive programmatic control

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

Open Spiel is a research library and framework for reinforcement learning, planning, and multi-agent game simulation. It provides a system for representing single-agent and multi-agent games across zero-sum, cooperative, and imperfect information scenarios. The project utilizes a standardized abstract game interface to decouple game logic from algorithms, allowing agents to run across different game types. It implements performance-critical logic in C++ with Python bindings and uses deterministic seeded simulation to ensure reproducibility for research benchmarking. The framework covers a br

Lab is a customizable 3D platform and research testbed designed for training and testing autonomous agents using reinforcement learning. It serves as a spatial AI training simulator where agents can be evaluated through navigation and puzzle-solving tasks. The environment allows for the definition of complex layouts and task behaviors through external scripting, enabling the generation of specific challenges for AI research. It supports both automated training via standard API bindings and manual agent control to validate simulation dynamics. The system utilizes a grid-based spatial represen

CARLA is an autonomous driving simulator and research environment designed for developing and validating self-driving software. It functions as an urban traffic simulator that generates realistic vehicle and pedestrian behavior and as a synthetic sensor data generator producing LiDAR, Radar, and camera data. The platform distinguishes itself through its deep integration with robotics frameworks, specifically providing native connectivity to ROS2 nodes for robotic control and data processing. It supports the training of driving models via imitation and reinforcement learning within a controlle

Dopamine is a reinforcement learning research framework designed for prototyping and testing algorithms across diverse simulated environments. It provides an agent development toolkit that utilizes a flat class hierarchy to facilitate the creation and extension of learning agents. The framework includes a standardization layer via environment wrappers that connect agents to various physics simulations and gaming environments. It also features a high-performance experience replay buffer for storing and sampling transition data to improve training stability, alongside a dedicated hyperparameter

Habitat-sim is a high-performance 3D simulation platform designed for training and benchmarking embodied AI agents within photorealistic indoor and outdoor environments. It serves as a simulator for AI and robotics, providing a system for generating synthetic data and simulating physical interactions. The project is distinguished by a native C++ core that enables high-throughput simulation and a rendering pipeline using physically based rendering and baked global illumination. It features a navigation system based on pre-computed navigation meshes to ensure collision-free traversal and a rigi

An API standard for multi-agent reinforcement learning environments, with popular reference environments and related utilities

Gym-anytrading is a reinforcement learning toolkit designed to simulate financial market conditions for the development and evaluation of automated trading agents. It provides a standardized framework that models stock and forex market data, allowing researchers to train agents through trial and error within consistent, gym-compatible environments. The platform distinguishes itself through an object-oriented architecture that enables users to define custom trading logic, including unique reward functions, profit calculations, and trade fee policies. By transforming raw financial datasets into

Malmo is a voxel-based simulation platform designed for artificial intelligence research and the study of autonomous agent behaviors. Built as a sandbox environment using Minecraft, it serves as a framework for multi-agent simulation and reinforcement learning research within a 3D grid of blocks. The project distinguishes itself through a multi-agent simulation framework that coordinates and synchronizes multiple autonomous agents to perform collaborative missions. It provides a standardized interface following reinforcement learning specifications, allowing it to function as an environment f

Rotors Simulator is a physics-based simulation framework designed for testing multirotor unmanned aerial vehicles and their control algorithms within a virtual environment. It models aerial vehicle movement, rotor thrust, and aerodynamic interactions by computing individual motor speeds directly to apply thrust and torque forces to rigid body dynamics. Aircraft kinematics, visual meshes, and sensor attachment points are described declaratively using unified robot description format files. The environment integrates dynamic models and aerodynamic forces through native runtime plugins while coo

Deep reinforcement learning GPU libraries for NVIDIA Jetson TX1/TX2 with PyTorch, OpenAI Gym, and Gazebo robotics simulator.

PufferLib is a reinforcement learning framework built around high-speed environment simulation and automatic hyperparameter optimization. It is designed to accelerate the entire RL training pipeline by running simulations at near-native speed and enabling the training of tiny models to super-human performance within seconds. The framework achieves its speed through a single-process training loop that eliminates inter-process communication overhead, vectorized batched simulation for parallel environment execution, and compiled C extensions that offload performance-critical computations. It als

A ROS/ROS2 Multi-robot Simulator for Autonomous Vehicles