Official TensorFlow implementation of the paper "Automating Reinforcement Learning with Example-based Resets"

SUNRISE: A Simple Unified Framework for Ensemble Learning in Deep Reinforcement Learning

A Git-compatible VCS that is both simple and powerful

Introduction to Machine Learning Systems

Standard Open Arm 100

A curated list of Rust code and resources.

A terminal workspace with batteries included

✨ Magical shell history

集找番、追番、看番的一站式弹幕追番平台，云收藏同步 (Bangumi)，离线缓存，BitTorrent，弹幕云过滤。100% Kotlin/Compose Multiplatform

Truly independent web browser

一款提示词优化器，助力于编写高质量的提示词

Utility to convert between various subscription format

美好世界你我相伴。同性恋🏳️‍🌈看过来，在这里找到我们的最爱！

A curated list of awesome mathematics resources

Author's PyTorch implementation of Randomized Ensembled Double Q-Learning (REDQ) algorithm.

Code at the speed of thought – Zed is a high-performance, multiplayer code editor from the creators of Atom and Tree-sitter.

[ICLR 2025] Robust Gymnasium: A Unified Modular Benchmark for Robust Reinforcement Learning.

[ICML 2025] Dual Random Network Distillation (DuRND): a reward shaping approach for exploration-exploitation balance.

Efficient seed-parallel implementation of "Breaking the Replay Ratio Barrier"

JAX (Flax) implementation of algorithms for Deep Reinforcement Learning with continuous action spaces.

Implementation of the paper "Improving Value Estimation Critically Enhances Vanilla Policy Gradient", ICML '25

The code implementation of Continual Churn Approximation Reduction (C-CHAIN) for ICML 2025 paper "Mitigating Plasticity Loss in Continual RL by Reducing Churn"

GlazeWM is a tiling window manager for Windows inspired by i3wm.

📚 从零开始的大语言模型原理与实践教程

历年ICLR论文和开源项目合集，包含ICLR2021、ICLR2022、ICLR2023、ICLR2024、ICLR2025.

High-quality single-file implementations of SOTA Offline and Offline-to-Online RL algorithms: AWAC, BC, CQL, DT, EDAC, IQL, SAC-N, TD3+BC, LB-SAC, SPOT, Cal-QL, ReBRAC

Customizable Reinforcement Learning

CleanDiffuser: An Easy-to-use Modularized Library for Diffusion Models in Decision Making

Run GGUF models easily with a KoboldAI UI. One File. Zero Install.

A context-aware AI assistant for your desktop. Ready to respond intelligently, seamlessly integrating multiple LLMs and MCP tools.