A collective list of free APIs

Learn how to design large-scale systems. Prep for the system design interview. Includes Anki flashcards.

ChatGLM-6B: An Open Bilingual Dialogue Language Model | 开源双语对话语言模型

[CVPR 2023] SadTalker：Learning Realistic 3D Motion Coefficients for Stylized Audio-Driven Single Image Talking Face Animation

PyTorch implementations of deep reinforcement learning algorithms and environments

《计算机网络－自顶向下方法(原书第6版)》编程作业，Wireshark实验文档的翻译和解答。

Google DeepMind's software stack for physics-based simulation and Reinforcement Learning environments, using MuJoCo.

Real time interactive streaming digital human

rllab is a framework for developing and evaluating reinforcement learning algorithms, fully compatible with OpenAI Gym.

AI Vtuber是一个由 【ChatterBot/ChatGPT/claude/langchain/chatglm/text-gen-webui/闻达/千问/kimi/ollama】 驱动的虚拟主播【Live2D/UE/xuniren】，可以在 【Bilibili/抖音/快手/微信视频号/拼多多/斗鱼/YouTube/twitch/TikTok】 直播中与观众实时互动 或 直接在本地进行聊…

Collection of reinforcement learning algorithms

Elegant PyTorch implementation of paper Model-Agnostic Meta-Learning (MAML)

A training framework for Stable Baselines3 reinforcement learning agents, with hyperparameter optimization and pre-trained agents included.

A toolkit for reproducible reinforcement learning research.

bsuite is a collection of carefully-designed experiments that investigate core capabilities of a reinforcement learning (RL) agent

High-fidelity performance metrics for generative models in PyTorch

Soft Actor-Critic

Reinforcement Learning with Model-Agnostic Meta-Learning in Pytorch

ucore os lab guide

MiniHack the Planet: A Sandbox for Open-Ended Reinforcement Learning Research

DeepRL algorithms implementation easy for understanding and reading with Pytorch and Tensorflow 2(DQN, REINFORCE, VPG, A2C, TRPO, PPO, DDPG, TD3, SAC)

An Implementation of Model-Agnostic Meta-Learning in PyTorch with Torchmeta

Python library for the Amadeus Self-Service travel APIs

Implementation of the variational continual learning method

Code for 'Dynamics-Aware Unsupervised Discovery of Skills' (DADS). Enables skill discovery without supervision, which can be combined with model-based control.

RelaxedIK Solver

Soft Actor-Critic

Diversity is All You Need: Learning Skills without a Reward Function in PyTorch.