Open-source alternatives to Dm Control

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

Stable-baselines3 is a reinforcement learning library built on the PyTorch deep learning framework. It provides a collection of reliable, standardized implementations of reinforcement learning algorithms designed for training, testing, and benchmarking agent policies in diverse simulated environments. The library functions as an agent training toolkit that emphasizes modularity and reproducibility. It features a unified environment interface and supports vectorized execution to accelerate data collection across multiple simulation instances. Users can customize neural network architectures, f

Chrono is a multi-physics simulation suite that functions as a multibody dynamics simulator, a finite element analysis tool, and a robotics simulation framework. It provides specialized solvers for fluid-solid interaction and distributed physics engines capable of synchronizing multiple agents across a network. The project features a dedicated pipeline for converting CAD assemblies into simulation-ready formats and integrates directly with robot operating systems to validate autonomous control logic and sensors. It differentiates itself through the use of WebAssembly for portable browser-base

jetson-inference is a set of libraries and tools for executing optimized deep learning models on embedded GPU hardware. Its primary purpose is to enable real-time computer vision and AI inference at the edge with low latency and high throughput. The project distinguishes itself through high-performance streaming analytics and the ability to execute concurrent AI pipelines on auto-grade silicon. It provides specialized support for multi-sensor stream processing, utilizing zero-copy data transport to load camera frames directly into GPU memory. The codebase covers a broad surface of capabiliti

This project is a game AI training framework designed to develop and monitor reinforcement learning agents within a legacy game environment. It functions as a training and monitoring system that optimizes autonomous agents to complete game objectives through exploration and reward-based learning. The framework includes tools for game memory mapping and real-time trajectory visualization. These capabilities translate raw game memory addresses into visual coordinates, allowing agent movements and session data to be streamed to a map for the analysis of navigation patterns and area exploration.

This project is a Python-based educational framework designed to simulate reinforcement learning algorithms and environments. It serves as a platform for reproducing classic textbook examples, allowing users to study agent behavior, policy improvement, and the fundamental mechanics of decision-making in controlled settings. The library provides implementations for core reinforcement learning concepts, including temporal difference learning, Monte Carlo episode sampling, and tabular value function approximation. It enables the analysis of specific algorithmic behaviors, such as identifying and

XLeRobot is an embodied AI robotics platform and hardware ecosystem designed for developing and deploying autonomous robots. It integrates a dual-arm mobile robot platform with an LLM-based robot controller, a physics-based simulation environment, and a teleoperation interface to translate natural language instructions into physical actions. The project emphasizes low-cost robot fabrication using 3D printing and affordable components to create a mobile base with interchangeable arms and grippers. It features a specialized teleoperation workflow that allows for remote hardware control via VR i

Genesis is an embodied AI simulation platform and parallelized robotics simulator designed for training general-purpose robotic agents. It integrates a physics engine for robotics that calculates collisions and movements for rigid bodies, soft tissues, and fluids, alongside a photorealistic 3D rendering engine. The platform features a domain randomization framework to vary environment parameters across parallel simulations, aiding in sim-to-real transfer. It supports the integration of real-world captured light fields and Gaussian splatting to provide photorealistic backgrounds within simulat

DeepMimic is a deep reinforcement learning framework and physics-based motion imitation tool designed to teach simulated characters and robots to reproduce human movements. It provides a pipeline for integrating motion capture data into physics simulations to train agents that can mimic complex physical skills. The system utilizes the PyBullet simulation environment to execute motion policies and visualize character interactions in real time. It includes a motion capture integration pipeline that imports and processes animation sequences to serve as reference targets for imitation learning ag

This project is an educational repository of reinforcement learning agents and tutorials implemented using TensorFlow. It provides a practical codebase for both model-free and model-based learning agents, designed to demonstrate how AI agents learn through trial and error. The collection features detailed implementations of various algorithmic approaches, including Deep Q-Networks and Policy Gradient methods. It specifically covers Actor-Critic architectures for continuous and discrete action spaces, alongside Proximal Policy Optimization and Deep Deterministic Policy Gradients. The framewor

DRL-robot-navigation is a deep reinforcement learning platform and robotic simulation framework designed to train autonomous mobile robots for collision-free path planning. It uses neural network policies and physics-engine simulation environments to teach robots how to navigate toward target coordinates while avoiding obstacles. The software trains continuous control policies using twin delayed deep deterministic policy gradients over continuous state and action spaces. Training is guided by scalar reward signals derived from target proximity and obstacle avoidance distances. System compone

This project is an educational resource designed to teach the mathematical foundations and core algorithms of reinforcement learning. It provides a structured academic curriculum that combines textbooks, lecture materials, and practical code examples to guide learners through the principles of Markov decision processes and reinforcement learning theory. The repository distinguishes itself by integrating a grid-based simulation framework that allows users to test algorithms within custom environments. This environment supports the analysis of agent performance by rendering state values, polici

This project provides a complete set of design files and hardware specifications for a 3D-printable industrial-style robot arm. The system includes a CAN bus robot controller for managing stepper motors and sensors, a kinematics engine for calculating joint angles and poses, and a UDP-based Python API for sending motion commands and monitoring telemetry. The system features a force-controlled robotic gripper that utilizes field-oriented control on stepper motors to enable compliant grasping and precise force sensing. It also includes a 3D position visualization tool for real-time telemetry tr

PyGame Learning Environment is a Python framework that provides a standardized interface for training artificial intelligence agents within diverse game environments. It functions as a communication layer that bridges reinforcement learning agents with game state observations, action inputs, and reward signals, allowing for consistent interaction across different game titles. The platform distinguishes itself by offering a headless execution mode that disables graphical rendering pipelines. By bypassing display overhead, this feature accelerates training cycles for automated agents during bac

JoltPhysics is a high-performance C++ physics engine designed for multi-threaded simulation of 3D rigid bodies and soft bodies. It serves as a deterministic simulation framework, ensuring identical results across different platforms and architectures to support networked synchronization. The engine distinguishes itself through a focus on concurrent execution across multiple CPU cores to handle large numbers of active bodies. It provides specialized systems for vehicle physics, including wheeled and tracked models, as well as soft body physics for deformable objects and cloth. The simulation

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 comprehensive software framework for autonomous robot navigation, providing a collection of algorithms for path planning, motion control, and trajectory generation. It serves as a toolkit for implementing and researching navigation logic, enabling the calculation of collision-free routes and the execution of precise movement commands for autonomous mobile agents. The library distinguishes itself by integrating both global pathfinding and real-time reactive control strategies. It supports diverse planning methodologies, including graph-based heuristic searches and sampling-ba

Legged Gym is a high-performance simulation platform and toolkit engineered for training autonomous robotic agents in complex, physics-based environments. It provides a comprehensive framework for developing legged locomotion control policies, enabling robots to learn movement strategies for navigating uneven terrain and managing physical disturbances through reinforcement learning. The platform distinguishes itself by utilizing hardware-accelerated physics and headless execution to maximize computational throughput during training. It incorporates a domain randomization pipeline that injects

Unitree RL Gym is an integrated software framework designed for the simulation, training, and deployment of motion control policies for legged robotic platforms. It provides a comprehensive environment for developing locomotion strategies for quadruped and humanoid robots by leveraging reinforcement learning algorithms within high-fidelity physics-based simulations. The platform distinguishes itself by offering an end-to-end workflow that bridges the gap between virtual training and physical execution. It includes specialized tools for mapping raw sensor data into normalized state-space obser

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

Tinker Cookbook is an open-source framework for fine-tuning large language models, supporting supervised learning, reinforcement learning, and parameter-efficient techniques like LoRA adapters. It provides a complete pipeline for aligning models with human preferences through multi-stage RLHF workflows, from supervised fine-tuning through preference optimization to reinforcement learning. The framework distinguishes itself through recipe-based training orchestration, where fine-tuning workflows are defined as composable recipe files that chain data loading, model configuration, and training l

ConvNetJS is a JavaScript deep learning library and neural network training engine designed for client-side machine learning. It functions as a framework for building, training, and running convolutional neural networks directly within a web browser without the need for a backend server. The library specializes in image recognition and pattern analysis using convolutional and pooling layers. It enables the creation of models for classification and regression tasks, as well as the development of reinforcement learning agents that optimize behavior through trial and error in simulated environme

MuJoCo is a physics simulation engine designed for the dynamics of multi-joint articulated structures. It provides a computational framework for calculating the forces, velocities, and physical interactions of complex models within a virtual environment, supporting research in robotics, biomechanics, and machine learning. The engine utilizes a constraint-based dynamics solver and recursive algorithms to manage the motion of articulated systems. It includes a native graphical interface for real-time visualization, allowing users to inspect physical behaviors and contact dynamics as they occur.

This project is an educational platform and research toolkit designed to teach deep learning through a combination of mathematical theory, visual diagrams, and executable code. It provides a comprehensive environment for building, training, and evaluating neural networks, grounding complex concepts in interactive computational notebooks that allow for hands-on experimentation. The framework distinguishes itself by interleaving theoretical foundations—including linear algebra, calculus, and probability—with practical implementations across multiple industry-standard libraries. It supports flex

Matter-js is a 2D rigid body physics engine written in JavaScript for simulating realistic physical interactions, collisions, and dynamics in web browsers. It functions as a web physics simulation library that calculates motion, gravity, and constraints for objects rendered on a web canvas. The library includes a built-in canvas physics visualizer to draw physical bodies, joints, and constraints for debugging and gameplay. It distinguishes itself through a plugin system that supports recursive dependency resolution and internal method patching to inject custom logic into the engine's executio

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

Gobot is a robotics framework for the Go programming language designed for developing robotics, drones, and IoT applications. It provides a hardware abstraction layer with standardized drivers to interact with GPIO, I2C, SPI, and PWM interfaces across various single-board computers and microcontrollers. The framework functions as an IoT device orchestrator and BLE device manager, enabling the coordination of multiple sensors, actuators, and Bluetooth Low Energy peripherals. It includes specialized interfaces for drone control, allowing for the management of flight maneuvers and video streams