An Easy-to-use, Scalable and High-performance RLHF Framework based on Ray (PPO & GRPO & REINFORCE++ & vLLM & Ray & Dynamic Sampling & Async Agentic RL)

AKShare is an elegant and simple financial data interface library for Python, built for human beings! 开源财经数据接口库

CVPR 2025(Highlight) DexGraspAnything: Towards Universal Robotic Dexterous Grasping with Physics Awareness

RWKV is an RNN with transformer-level LLM performance. It can be directly trained like a GPT (parallelizable). So it's combining the best of RNN and transformer - great performance, fast inference,…

Awesome In-Context RL: A curated list of In-Context Reinforcement Learning - - —

Next-gen Foundation Model for Embodied AI

Non-official implementation of paper "In-context Reinforcement Learning with Algorithm Distillation"

Simple and easily configurable 3D FPS-game-like environments for reinforcement learning

Worker to orchestrate and manage running an arbitrary number of LLM-generated builds concurrently using containerized Minecraft Servers.

🚀 Efficient implementations of state-of-the-art linear attention models

Unified framework for robot learning built on NVIDIA Isaac Sim

An experimental maze built with Python and OpenGL.

A modular high-level library to train embodied AI agents across a variety of tasks and environments.

🏘️ Scaling Embodied AI by Procedurally Generating Interactive 3D Houses

A Python 3D Engine

Unofficial implementation of Linear Recurrent Units, by Deepmind, in Pytorch

Xenoverse is a collection of randomized RL, Language, and general-purpose simulation environments, designed for training General-Purpose Learning Agents (GLAs).

Baselines for Lifelong Learning in Context

Implementation of Generating Diverse High-Fidelity Images with VQ-VAE-2 in PyTorch

Vector Quantized VAEs - PyTorch Implementation

Collection of Reinforcement Learning / Meta Reinforcement Learning Environments.

Air to air combat sandbox, created in Python 3 using the HARFANG 3D 2 framework.

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

Easy-to-use and powerful LLM and SLM library with awesome model zoo.

Implementations of the algorithms described in Differentiable plasticity: training plastic networks with gradient descent, a research paper from Uber AI Labs.