A non-saturating, open-ended environment for evaluating LLMs in Factorio

Production-tested AI infrastructure tools for efficient AGI development and community-driven innovation

A PyTorch native library for large model training

Efficient Triton Kernels for LLM Training

continuous level of detail mesh library

Infinite Photorealistic Worlds using Procedural Generation

PlayStation 4 emulator for Windows, Linux and macOS written in C++

Implementation of Vision Transformer, a simple way to achieve SOTA in vision classification with only a single transformer encoder, in Pytorch

A generative world for general-purpose robotics & embodied AI learning.

Multi-Agent Reinforcement Learning with JAX

Collections of robotics environments geared towards benchmarking multi-task and meta reinforcement learning

Official implementation of the RLC 2024 paper "Policy-Guided Diffusion"

A benchmark for offline goal-conditioned RL and offline RL

Jax/Flax Implementation of TD-MPC2

Elucidating the Design Space of Diffusion-Based Generative Models (EDM)

DIAMOND (DIffusion As a Model Of eNvironment Dreams) is a reinforcement learning agent trained in a diffusion world model. NeurIPS 2024 Spotlight.

Tile primitives for speedy kernels

A library to analyze PyTorch traces.

Higher level programming in C

JMLR: OmniSafe is an infrastructural framework for accelerating SafeRL research.

Constrained Policy Optimization

Galactic Scaling End-to-End Reinforcement Learning for Rearrangement at 100k Steps-Per-Second

A library for differentiable robotics.

Development repository for the Triton language and compiler

Model API for GALACTICA

[Unmaintained, see README] An ecosystem of Rust libraries for working with large language models