ICLR 2026: Towards Bridging the Gap between Large-Scale Pretraining and Efficient Finetuning for Humanoid Controls

MR.Q is a general-purpose model-free reinforcement learning algorithm.

Official Code for "Relative Entropy Pathwise Policy Optimization"

Code for "SimbaV2: Hyperspherical Normalization for Scalable Deep Reinforcement Learning"

Web browser add-on that prevents YouTube's automatic translations! It keeps titles, descriptions, and audio in their original language.

RL Baselines3 Zoo training environment for Upkie wheeled bipeds

Actor-Free Continuous Control via Structurally Maximizable Q-Functions

DSAC-v2-StableBaselines3

💡 All-in-one AI framework for semantic search, LLM orchestration and language model workflows

A C# Unity mod and Python Socket server for training Reinforcement Learning agents to fight Hollow Knight: Silksong boss encounters

Open-Source Frontier Voice AI

Create detailed, textured 3D meshes of anything from a short smartphone video.

Terminal Network scanner & diagnostic tool with modern TUI

A Modular Toolkit for Robot Kinematic Optimization

Fullstack app framework for web, desktop, and mobile.

This repository contains Reinforcement Learning (RL) environments for the Upkie robot.

Transcription server and library written in Rust

RAG on Everything with LEANN. Enjoy 97% storage savings while running a fast, accurate, and 100% private RAG application on your personal device.

Why is this running?

simple terminal UI for git commands

Beautiful, Modern & Opinionated Linux

The lazier way to manage everything docker

A monitor of resources