SVL: Goal-Conditioned Reinforcement Learning as Survival Learning

BullshitBench measures whether AI models challenge nonsensical prompts instead of confidently answering them, created by Peter Gostev.

Bibliography database for machine learning conferences.

Making it easier to work with shaders

Scalable drone simulation using JAX.

Nonlinear optimisation (root-finding, least squares, ...) in JAX+Equinox. https://docs.kidger.site/optimistix/

Guided Flow Policy: Learning from High-Value Actions in Offline RL

[NeurIPS'21 Outstanding Paper] Library for reliable evaluation on RL and ML benchmarks, even with only a handful of seeds.

JAX-based library for offline and online off-policy reinforcement learning

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

Reinforcement learning in differentiable multiphysics simulation with NVIDIA Warp.

A minimal(ish) reinforcement learning library that aggregates reliable implementations.

Inria fork of Pinocchio for fast developments and fixes

A support library for bindings between Eigen in C++ and Python, based on nanobind

A cross-platform real-time 3D renderer for robotics powered by SDL3-gpu

A common interface and utilities for implementing visualizers for Pinocchio in C++.

Simple C++ abstraction layer for quadratic programming solvers using Eigen.

OUTDATED Team website -- use private willowsierra/willow_webpage

Benchmarking contact models and solvers from robotics simulators.

Low-Complexity Inverse Kinematics

Python/C++ library for Dynamical Movement Primitives and Black-Box Optimization

The Simple Simulator: Simulation Made Simple

Educational Python library for manipulator motion planning

Access 185+ robot descriptions from the main Python robotics frameworks

Implement a ChatGPT-like LLM in PyTorch from scratch, step by step

Open-source wheeled biped robots

Course to get into Large Language Models (LLMs) with roadmaps and Colab notebooks.