30 open-source projects similar to google-deepmind/pysc2, ranked by shared indexed features. Tags may describe platforms or build tools rather than the same primary purpose. Check each project’s use case, license, and deployment requirements before treating it as a replacement.
pysc2 is a Python interface and simulation framework that connects the StarCraft II game engine to machine learning agents. It acts as an API wrapper that exposes game internals as a set of observations and actions, providing a reinforcement learning environment for research and training. The framework includes tools for game replay analysis to extract data and sequences of actions from recorded matches for predictive modeling. It also provides an agent simulation environment to run and evaluate the performance of single or competing artificial intelligence agents. The system handles game ma
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
Universe is a training and evaluation platform that transforms websites, games, and software into standardized environments for general intelligence agents. It functions as a reinforcement learning wrapper and remote environment orchestrator, providing a consistent interface to wrap diverse software for AI agent interaction. The platform distinguishes itself through a visual observation interface that streams real-time pixel data and transmits keyboard and mouse events to simulate human interaction. It utilizes a bi-directional communication protocol to deliver reward signals and performance
DeepMind Lab is a customisable three-dimensional simulation platform for training and evaluating learning agents. It is built on a modified fork of the Quake III Arena engine, adapted to render first-person worlds for agents rather than human players. The engine is written in C++ and built with Bazel, and it is exposed to Python so environments can be created, stepped, reset and observed from scripts, including through a standard reinforcement learning interface. The platform ships with a suite of navigation and puzzle-solving tasks, along with ready-made levels that test specific mental abil
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
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
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
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
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
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
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.
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
keras-rl is a reinforcement learning library that enables the training of neural agents using Keras. It serves as a framework for implementing deep reinforcement learning agents that interact with simulated environments to discover optimal behaviors and maximize cumulative rewards. The library provides a system for configuring, training, and managing neural network agents. It handles the interaction loop between agents and environments, allowing models to learn through direct experience and gradient-based optimization. The framework includes capabilities for model weight management, allowing
OSWorld is an evaluation framework and multimodal agent benchmark designed to test the ability of large language models to complete complex tasks within virtualized operating system environments. It provides a virtualized desktop sandbox and a virtual machine orchestrator to deploy, snapshot, and reset cloud-based desktops, ensuring reproducible test states for AI agent interactions. The system distinguishes itself by providing an OS-level action space that translates model decisions into mouse clicks, keyboard inputs, and system commands. It employs a standardized interface to integrate vari
LLM-RL-Visualized is a visual reference library and collection of knowledge maps designed to explain Large Language Model and Reinforcement Learning algorithms. It provides a structured system of conceptual diagrams and taxonomies covering the intersection of language model alignment and reinforcement learning. The project distinguishes itself through detailed visual mappings of complex workflows, such as the coordination of reward models and policy optimization in reinforcement learning from human feedback. It contrasts different preference optimization architectures, such as RLHF and Direct
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
Minigo is a TensorFlow-based reinforcement learning engine designed to master the game of Go. It functions as a comprehensive system for training neural networks to predict board policies and game outcomes, utilizing a model trainer to generate self-play data and optimize weights. The project is distinguished by its ability to perform large-scale game simulations using Kubernetes to distribute worker nodes across CPU, GPU, and TPU hardware. It employs a Monte Carlo Tree Search implementation to identify optimal moves and supports specialized hardware acceleration, including inference on Edge
DouZero is a deep reinforcement learning framework and training system designed to teach digital agents to master complex card games. It provides the infrastructure to implement high-throughput reinforcement learning pipelines and evaluate the competitive success of game agents. The system utilizes a distributed actor-learner architecture that separates game simulation actors from GPU training devices to accelerate model convergence. It combines Monte Carlo Tree Search with policy-based value estimation to determine optimal moves through recursive evaluation and random sampling. The toolkit
Grasscutter is a private game server emulator designed to replicate game backend logic and simulate core gameplay mechanics without the use of official servers. It functions as a system for simulating character progression, world entities, and general backend simulation to host a private instance of a specific anime game. The project includes a game object management console for spawning entities and controlling player inventories within the simulated environment. It also provides a server configuration tool featuring a guided interface to generate and manage the settings and configuration fi
This project is a Chinese language translation of the technical guides and API references for the PyTorch deep learning framework. It serves as a localized knowledge base and reference material to make deep learning documentation accessible to non-English speakers. The documentation covers a comprehensive range of PyTorch capabilities, including neural network model development, automatic differentiation, and the implementation of backend kernels. It provides detailed guidance on distributed training strategies, model deployment through formats like ONNX and C++, and various model optimizatio
FinRL is a reinforcement learning framework designed for the development, training, and backtesting of automated trading strategies. It functions as a quantitative finance toolkit that integrates deep learning algorithms with financial market simulations to address complex portfolio management and asset allocation tasks. The platform provides an end-to-end pipeline for transforming raw market data into actionable trading models. The project distinguishes itself through a layered, modular architecture that separates data processing, environment simulation, and agent training. This design allow
Horizon is a reinforcement learning platform designed for training, evaluating, and deploying agents and contextual bandits using historical data. It serves as an off-policy engine and offline policy evaluation tool, allowing decision-making policies to be optimized and tested without the need for a live simulator. The framework specializes in recommendation system optimization, specifically using slating-based reinforcement learning to optimize the ordering and sequencing of multiple recommendations. It also functions as a contextual bandit framework that manages the balance between explorat
This project is a deep reinforcement learning agent and AI game automation tool designed to master game objectives by analyzing visual input. It implements a Deep Q-Network to train an autonomous bot that learns to play a video game by maximizing rewards through deep Q-learning. The system utilizes a convolutional neural network to process raw pixel data from game frames, identifying patterns to determine optimal real-time actions. Training is stabilized through the use of an experience replay buffer and an epsilon-greedy action selection strategy to balance exploration and exploitation. The
This project is a comprehensive platform for quantitative investment research, machine learning, and algorithmic trading. It provides an end-to-end environment for developing, testing, and executing financial strategies, supporting the entire lifecycle from data ingestion and feature engineering to model training and backtesting. The system is distinguished by its configuration-driven workflow orchestration, which allows researchers to automate complex pipelines and manage experiments through declarative files. It features a high-performance data infrastructure that utilizes custom binary for
Easy-RL is an educational resource designed to teach the principles and implementation of reinforcement learning. It provides a structured curriculum that guides users from fundamental concepts to advanced algorithmic techniques, focusing on the development and training of autonomous agents that learn through interaction with simulated environments. The project distinguishes itself through a pedagogical framework that utilizes interactive notebooks to bridge the gap between theoretical research and functional code. By organizing complex methods into modular units, it allows for the study of i
This project is a comprehensive collection of practical code examples and implementation libraries for machine learning. It provides a wide array of reference materials for building supervised, unsupervised, and reinforcement learning algorithms. The repository serves as a multi-domain resource, featuring specific implementation suites for financial AI, Bayesian statistical modeling, and deep learning architectures. It includes a framework for training intelligent agents using policy gradients and actor-critic models, as well as practical guides for fine-tuning transformers and utilizing larg
Beyond-All-Reason is a real-time strategy game and 3D military simulation focused on large-scale tactical combat, base building, and resource management. It functions as a competitive multiplayer platform featuring ranked lobbies and skill-based matchmaking. The project includes a custom map editor for designing unique game levels and environments through structural and thematic configuration. The simulation covers military-industrial economy management, including resource extraction and asset recovery. Tactical gameplay involves commanding army formations, using radar for enemy unit detecti
Warzone 2100 is an open-source real-time strategy game engine focused on tactical combat and base building. It operates as a real-time strategy game engine utilizing a data-driven asset pipeline and providing cross-platform support. The project features a modular unit design system that uses a technology tree to construct combat entities by combining chassis, propulsion, and weapon components. It includes a lockstep multiplayer network engine to synchronize game state across distributed clients for competitive matches, as well as a JavaScript game scripting framework for implementing custom l
This project is a real-time strategy game and military combat simulator focused on modern warfare. It provides a simulation where players build bases and command military units to achieve tactical objectives and execute combat operations across various global locations. The software functions as a user-generated content platform, featuring a community workshop for creating, uploading, and sharing custom maps. It also includes a narrative-driven single-player campaign consisting of a series of strategic missions. Gameplay involves battling computer-controlled commanders that utilize distinct