lyu-xg

AI_coursework

AlexaSkill

alfred-latex-symbols-workflow

:mag_right: Alfred 2/3 workflow to search for latex symbol commands

Algo_courcework

brownClustering

brownClustering

dec-hdrqn

nlp-practice

coding space for NLP

on-centralized-critics-in-marl

UniversityRankingSystem

lyu-xg/dec-hdrqn

lyu-xg/on-centralized-critics-in-marl

lyu-xg/ApplesAndOranges

lyu-xg/bilingual_book_maker

Make bilingual epub books Using AI translate

lyu-xg/DTQN

Deep Transformer Q-Networks for Partially Observable Reinforcement Learning

lyu-xg/equi_q_corl21

This repository contains the code of the paper Equivariant Q Learning in Spatial Action Spaces

lyu-xg/G-DICE

Stores G-DICE code as I convert it

lyu-xg/gym-BinPack3D

lyu-xg/gym-gridverse

Gridworld domains in the gym interface

lyu-xg/helping_hands_rl_envs

lyu-xg/JaxMARL

Multi-Agent Reinforcement Learning with JAX

lyu-xg/lyu-xg.github.io

blog

lyu-xg/MAAC

Code for "Actor-Attention-Critic for Multi-Agent Reinforcement Learning" ICML 2019

lyu-xg/maddpg

Code for the MADDPG algorithm from the paper "Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environments"

lyu-xg/marl_envs

collection of MARL environments

lyu-xg/mujoco-py

MuJoCo is a physics engine for detailed, efficient rigid body simulations with contacts. mujoco-py allows using MuJoCo from Python 3.

lyu-xg/Multi-Agent-Reinforcement-Learning-Environment

Hello, I pushed some python environments for Multi Agent Reinforcement Learning.

lyu-xg/multiagent-particle-envs

Code for a multi-agent particle environment used in the paper "Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environments"

lyu-xg/muzero-general

MuZero

lyu-xg/netlify-templates-solid-quickstart

lyu-xg/omniboard

Web-based dashboard for Sacred

lyu-xg/PettingZoo

Gym for multi-agent reinforcement learning

lyu-xg/rebiber

A simple tool to update bib entries with their official information (e.g., DBLP or the ACL anthology).

lyu-xg/rl-parsers

lyu-xg/RODE

Codes accompanying the paper "RODE: Learning Roles to Decompose Multi-Agent Tasks (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.

lyu-xg/sacred

Sacred is a tool to help you configure, organize, log and reproduce experiments developed at IDSIA.

lyu-xg/SE2-equivariant-grasp-learning

Code for the paper Sample Efficient Grasp Learning Using Equivariant Models

lyu-xg/smac

SMAC: The StarCraft Multi-Agent Challenge

lyu-xg/starter-academic

lyu-xg/tianshou

An elegant PyTorch deep reinforcement learning library.