TARTRL

TiKick

Learning-based agent for Google Research Football (足球游戏智能体)

Deepfake_Detection

deepfake detection codes, distributed pytorch training (AI换脸检测)

RankingCost

The Ranking Cost algorithm for multi-path routing of gridworld.(多智能体路径规划，电路规划)

TLaunch

Launch programs on multiple hosts. (多机启动程序)

TiZero

Code accompanying the paper "TiZero: Mastering Multi-Agent Football with Curriculum Learning and Self-Play" (AAMAS 2023) 足球游戏智能体

PyTorch_Tutorial

PyTorch使用技巧和教程

TARTRL

基于PyTorch的分布式强化学习框架

DGPO

code for DGPO: Discovering Multiple Strategies with Diversity-Guided Policy Optimization

examples

A set of examples around TLaunch in Reinforcement Learning, Vision, NLP, etc.

.github

FeverBasketballOpenSource

This project is the open-source of Fever Baksetball environment for research purpose.

hok_env

pai

Resource scheduling and cluster management for AI

reverb

Reverb is an efficient and easy-to-use data storage and transport system designed for machine learning research

criticality_score

Gives criticality score for an open source project

openrl

Unified Reinforcement Learning Framework

TARTRL-docs

TARTL文档