Open-source alternatives to Arcade Learning Environment

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

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

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

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.

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

ElegantRL is a deep reinforcement learning framework and quantitative trading platform designed for automating financial decision making. It provides a system for designing and training agents using massively parallel GPU execution and includes a coordination layer for multi-agent reinforcement learning. Additionally, it features a GPU-based solver for NP-complete and nonconvex mathematical optimization problems. The platform distinguishes itself through GPU-accelerated environments that simulate thousands of parallel market interactions on a single device to accelerate data collection. It in

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

This repository serves as a comprehensive collection of reference implementations for the PyTorch machine learning library. It provides practical examples for building, training, and deploying deep learning models, functioning as a toolkit for developers to explore neural network architectures and training workflows. The project distinguishes itself by offering concrete demonstrations of complex machine learning operations, ranging from computer vision tasks like object detection and depth estimation to the training of large-scale transformer models. These examples illustrate how to implement

PyBoy is a programmable Game Boy emulator and hardware simulation framework written in Python. It functions as an emulation engine that allows users to execute original handheld software while providing a programmatic interface to control, probe, and automate game execution. The project is specifically designed as a reinforcement learning environment, exposing emulator states and controls to facilitate the training of machine learning agents. It distinguishes itself by providing tools for game area mapping and the extraction of simplified 2D screen representations and collision maps to suppor

mlxtend is a pure Python machine learning extension library that provides additional tools for association rule mining, ensemble learning, and feature selection. It is built on numpy and pandas, with all data operations accepting and returning pandas DataFrames, and custom estimators inherit from scikit-learn’s base classes to offer a uniform fit-predict interface compatible with grid search. The library implements the Apriori algorithm for mining frequent itemsets from transaction data and generating association rules with confidence and lift metrics. For classification, it combines multiple

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

mlfinlab is a Python machine learning library for finance designed for building and validating models used in quantitative trading and portfolio management. It provides a financial data engineering toolkit and a quantitative strategy backtesting framework to transform raw market data into predictive signals and target classes. The library includes a synthetic financial data generator to create artificial datasets that mimic the statistical properties of real assets for stress testing. It also provides specialized tools for financial time series labeling and sampling to prevent data leakage in

This is a Python machine learning library featuring a collection of core algorithms implemented from scratch to demonstrate foundational AI concepts. It provides a comprehensive toolkit for supervised learning, unsupervised learning, and neural network development. The project is distinguished by its custom implementation of a neural network framework, which includes multi-layer perceptrons with backpropagation, gradient descent, and weight regularization. It also includes a specialized anomaly detection toolkit that identifies outliers and rare events using Gaussian probability distributions

This project is a collection of foundational machine learning algorithms and data science tools implemented in Python. It focuses on building the logic of these tools using basic programming primitives rather than relying on specialized libraries. The implementation covers several core domains, including a linear algebra library for matrix and vector operations, a statistical analysis toolkit for probability and hypothesis testing, and a framework for map-reduce distributed processing. It also includes implementations for natural language processing, graph theory for network analysis, and var

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

This project is a Python machine learning library and data science toolkit designed for building predictive models and analyzing complex datasets. It provides a collection of implementations for common supervised and unsupervised algorithms using the Scikit-Learn framework. The toolkit includes a predictive modeling suite for generating predictions from historical data and a statistical analysis framework for applying Bayesian modeling and causality tests. It also features a data visualization suite based on Matplotlib for rendering static charts and graphs to interpret classifier boundaries

Datasets is a library designed for the management, processing, and sharing of large-scale data collections for machine learning workflows. It functions as both a data processing framework and a versioning platform, providing tools to organize, filter, and transform massive datasets while ensuring reproducibility across research and development teams. The library distinguishes itself by enabling the handling of datasets that exceed available system memory. It utilizes memory-mapped file access, disk-based caching, and lazy iterative streaming to maintain performance when working with large-sca

ML for Hackers is a machine learning educational resource and library designed for learning the fundamentals of algorithmic programming and data analysis. It provides a neural network framework and a collection of mathematical implementations for building and training predictive models. The project utilizes a modular architecture for stacking linear transformations and activation layers. It implements core deep learning components from scratch using multi-dimensional arrays for tensor algebra and operations. The framework covers a variety of algorithmic capabilities, including automatic diff

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

dlib is a C++ machine learning toolkit and data analysis framework. It provides a collection of algorithms and utilities for building predictive modeling applications and performing statistical analysis on large datasets within native C++ environments. The project functions as a binding library that wraps low-level C++ machine learning algorithms into high-level Python scripting interfaces. This allows for the integration of high-performance native implementations with Python for machine learning development. The framework covers the implementation of predictive models, the execution of mach

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

Featuretools is an automated feature engineering library and data transformation framework written in Python. It automatically generates machine learning feature vectors from multi-table datasets by applying synthesis patterns to relational and timestamped data. The system functions as a distributed feature synthesis engine, allowing the process of creating feature vectors to scale across multiple cores or clusters to handle large-scale datasets. The library supports the synthesis of multi-table datasets, time series feature generation, and the creation of custom machine learning primitives

PRML is a Python machine learning library and statistical learning toolkit. It provides code implementations of supervised and unsupervised learning concepts, including regression, classification, and neural network algorithms for statistical data modeling. The project functions as a pattern recognition toolkit used to identify theoretical structures within numerical datasets. It includes a neural network framework for solving nonlinear data mappings and a linear algebra toolkit that utilizes vectorized operations and matrix calculations. The library covers a broad range of capabilities, inc

Video-Pre-Training is a machine learning framework designed for training autonomous agents to perform complex tasks by observing and mimicking human behavior from video recordings. It provides a comprehensive toolkit for imitation learning and reinforcement learning research, enabling the development of agents that can replicate human actions within simulated digital environments. The framework distinguishes itself through its ability to process large-scale, unlabeled video datasets to bootstrap agent capabilities. It utilizes inverse dynamics modeling to infer control inputs from frame trans

imbalanced-learn is a dataset balancing framework and Python machine learning extension designed to resample training data and reduce the impact of class imbalance. It provides a toolkit of algorithms for adjusting class distributions to improve model performance on minority class prediction. As a scikit-learn resampling library, it extends the ecosystem with specialized tools for balancing datasets through over-sampling and under-sampling techniques. This allows for the correction of skewed class proportions to reduce model bias toward the majority class. The library implements the scikit-l

This project is a comprehensive deep reinforcement learning course and training platform. It provides a structured educational curriculum that combines theoretical lessons with hands-on tutorials to teach the implementation of neural networks and agent behavior. The platform integrates a model sharing hub where users can upload, download, and version trained machine learning models. It also features a benchmarking system that uses leaderboards to evaluate and compare agent performance against community standards. The educational experience is delivered through interactive notebooks and inclu

An interactive Python code notebook and machine learning tutorial repository, this project provides a collection of instructional guides and code examples explaining data science concepts and predictive modeling techniques. It specifically functions as a scikit-learn tutorial notebook containing educational documents that demonstrate machine learning algorithms and practical workflows. The repository supports data science tutorial authoring, machine learning education, and interactive notebook learning. It organises content into sequential, self-contained computational steps that combine narr