ArronDZhang's starred repositories
awesome-game-ai
Awesome Game AI materials of Multi-Agent Reinforcement Learning
RODE
Codes accompanying the paper "RODE: Learning Roles to Decompose Multi-Agent Tasks (ICLR 2021, https://arxiv.org/abs/2010.01523). RODE is a scalable role-based multi-agent learning method which effectively discovers roles based on joint action space decomposition according to action effects, establishing a new state of the art on the StarCraft multi-agent benchmark.
google-research
Google Research
deep_bisim4control
Learning Invariant Representations for Reinforcement Learning without Reconstruction
transferlearning
Transfer learning / domain adaptation / domain generalization / multi-task learning etc. Papers, codes, datasets, applications, tutorials.-迁移学习
NLP-Projects
word2vec, sentence2vec, machine reading comprehension, dialog system, text classification, pretrained language model (i.e., XLNet, BERT, ELMo, GPT), sequence labeling, information retrieval, information extraction (i.e., entity, relation and event extraction), knowledge graph, text generation, network embedding
awesome-deep-rl
For deep RL and the future of AI.
MARL-Papers
Paper list of multi-agent reinforcement learning (MARL)
pytorch-DRL
PyTorch implementations of various Deep Reinforcement Learning (DRL) algorithms for both single agent and multi-agent.
MARL-Algorithms
Implementations of IQL, QMIX, VDN, COMA, QTRAN, MAVEN, CommNet, DyMA-CL, and G2ANet on SMAC, the decentralised micromanagement scenario of StarCraft II
awesome-reinforcement-learning
Learning Resources And Links Of Reinforcement Learning (updating)
pytorch-original-transformer
My implementation of the original transformer model (Vaswani et al.). I've additionally included the playground.py file for visualizing otherwise seemingly hard concepts. Currently included IWSLT pretrained models.
ijcai-2018
ijcai-2018 top1 solution
design-pattern
Python3实现设计模式,致力于将设计模式的**应用在开发中。创建型模式有:简单工厂模式、工厂方法模式、抽象工厂模式、 建造者模式和单例模式;结构型模式:适配器模式、桥模式、组合模式、外观模式和代理模式;行为型模式:责任链模式、观察者模式、策略模式和模板方法模式。设计模式是对软件设计中普遍存在或反复出向的各种问题所提出的解决方案。每一个设计模式系统地被命名、解释和评价了面向对象系统中一个重要和重复出现的设计。
pytorch_geometric
Graph Neural Network Library for PyTorch
filter-grafting
Filter Grafting for Deep Neural Networks(CVPR 2020)
translations
🐼 Chinese translations for classic software development resources