Pinned Repositories
baselines
OpenAI Baselines: high-quality implementations of reinforcement learning algorithms
Deep-Policy-Gradient
Use basic deep reinforcement learning to solve Doom health gathering environment
deepmind_MAS_enviroment
some Multiagent enviroment in 《Multi-agent Reinforcement Learning in Sequential Social Dilemmas》 and 《Value-Decomposition Networks For Cooperative Multi-Agent Learning》
GASIL
Independent Generative Adversarial Self-Imitation Learning In Cooperative Multiagent Systems
ICML-2020-MSBCB
Code of ICML-2020 paper Dynamic Knapsack Optimization Towards Efficient Multi-Channel Sequential Advertising
MA-MuZero
MuZero for Combinatorial Action Spaces: open-source codebase for MA-Gumbel-AlphaZero, MA-Sampled-AlphaZero, MA-Gumbel-MuZero and MA-Sampled-MuZero, from "Multiagent Gumbel MuZero: Efficient Planning in Combinatorial Action Spaces" at AAAI 2024.
pymarl3
We extend pymarl2 to pymarl3, equipping the MARL algorithms with permutation invariance and permutation equivariance properties. The enhanced algorithm achieves 100% win rates on SMAC-V1 and superior performance on SMAC-V2.
Qfamily_for_MatrixGame
We provide a very simple implementation of the typical value decomposition methods for solving single state Matrix Games.
RL_paper
SC1
tjuHaoXiaotian's Repositories
tjuHaoXiaotian/bootstrap
The most popular HTML, CSS, and JavaScript framework for developing responsive, mobile first projects on the web.
tjuHaoXiaotian/es
JavaEE项目开发脚手架
tjuHaoXiaotian/jquery_pagination
A Pagination module for jQuery
tjuHaoXiaotian/kandroid
KAndroid是一个Android的简单的架构搭建的学习项目。架构上分为了四个层级:模型层、接口层、核心层和应用层。
tjuHaoXiaotian/lanyuan
开放源码,基于springMVC+springSecurity3.x+Mybaits3.x的权限系统,,支持开源
tjuHaoXiaotian/tut-spring-security-and-angular-js
Spring Security and Angular JS:: A tutorial on how to use Spring Security with a single page application with various backend architectures, ranging from a simple single server to an API gateway with OAuth2 authentication.