aqt: Another (unofficial) Qt CLI Installer on multi-platforms

[NeurIPS 2025] The official implementation of "Towards Robust Zero-Shot Reinforcement Learning"

LeanRL is a fork of CleanRL, where selected PyTorch scripts optimized for performance using compile and cudagraphs.

GPU-Accelerated Multi-Agent Reinforcement Learning for High-Frequency Trading

Procgen2: A community maintained fork of procgen

A framework for creating rich, 3D, Minecraft-like single and multi-agent environments for AI research. (Accepted at ICML 2025).

A Curated List of Awesome Works in World Modeling, Aiming to Serve as a One-stop Resource for Researchers, Practitioners, and Enthusiasts Interested in World Modeling.

You like pytorch? You like micrograd? You love tinygrad! ❤️

Causal Responsibility EXplanations for Image Classifiers and Tabular Data

Reinforcement learning library from Embark Studios

Gym-TORAX: A software for integrating reinforcement learning with plasma control simulators

RL gym for vision language models written from scratch

ray & RLlib tools for unified code across different repositories. Experiments with dynamic hyperparameters

Ongoing Lean formalisation of the proof of Fermat's Last Theorem

Isaac Lab API, powered by MuJoCo-Warp, for RL and robotics research.

[ICML 2024, Spotlight] EfficientZero V2: Mastering Discrete and Continuous Control with Limited Data

Extension of Gymnasium for active perception tasks.

gpt-oss-120b and gpt-oss-20b are two open-weight language models by OpenAI

Modular Reinforcement Learning (RL) library (implemented in PyTorch, JAX, and NVIDIA Warp) with support for Gymnasium/Gym, NVIDIA Isaac Lab, Brax and other environments

[ 👾 ] ➡️ 💾 ➡️ { 🎮🕹️ } Extra Stable-Baselines3 buffer classes. Reducing RL memory usage drastically with minimal overhead.

A benchmark for offline goal-conditioned RL and offline RL

Ray is an AI compute engine. Ray consists of a core distributed runtime and a set of AI Libraries for accelerating ML workloads.

Settlers of Catan Bot Simulator and Strong AI Player

Unified framework for robot learning built on NVIDIA Isaac Sim