qmix 开源项目推荐（24 个）

agi-brain /xuance

XuanCe: A Comprehensive and Unified Deep Reinforcement Learning Library

Lizhi-sjtu /MARL-code-pytorch

Concise pytorch implements of MARL algorithms, including MAPPO, MADDPG, MATD3, QMIX and VDN.

huawei-noah /xingtian

星天是一个用于强化学习算法开发和验证的组件化库

yangchen1997 /Multi-Agent-Reinforcement-Learning

PyTorch implements multi-agent reinforcement learning algorithms, including QMIX, Independent PPO, Centralized PPO, Grid Wise Control, Grid Wise Control+PPO, Grid Wise Control+DDPG.

jianzhnie /deep-marl-toolkit

MARLToolkit: The Multi-Agent Rainforcement Learning Toolkit. Include implementation of MAPPO, MADDPG, QMIX, VDN, COMA, IPPO, QTRAN, MAT...

jk96491 /SMAC

该项目在 GitHub 上没有填写描述

Tviskaron /pogema-baselines

PPO and PyMARL baseline for Pogema environment

jianzhnie /RLToolkit

RLToolkit is a flexible and high-efficient reinforcement learning framework. Include implementation of DQN, AC, ACER, A2C, A3C, PG, DDPG, TRPO, PPO, SAC, TD3 and ....

Zhiyu014 /MARL-UDS

Source code for the MARL-enabled real-time control of urban drainage system

xlnwel /grl

General-Purpose Reinforcement Learning

tocom242242 /qmix_tf2

QMIX implemented in TensorFlow 2

jk96491 /C-COMA

Continual Multi-agent Reinforcement Learning in Dynamic Environments

Aravinthan404 /marl-qmix

Scalable Multi-Agent Reinforcement Learning with IQL and QMIX — from-scratch implementation in a custom grid environment. Compare independent vs centralized learning as agents scale from 2 to 10.

sswun /RAVEN

RAVEN: Receiver-conditioned Action-Value ENcoding for finite-symbol (2-bit) multi-agent communication

S-M-Projects /Object-Detection-the-Neuromatch-Project

A comparison between single agent and multi agent framework for object localization.

gmontana /modMARL

Modular cooperative multi-agent reinforcement learning with communication, reproducible demos and explicit validation evidence.

MohamedMohy10 /Cooperative-warehouse-agents-using-marl

JKU Msc POC course project

sqdjm /L-GRAFT

该项目在 GitHub 上没有填写描述

NadavFireman /Multi-Agent-Reinforcement-Learning-HW3-Value-Decomposition

Multi-Agent RL HW3 (Grade 97, M.Sc. Data Science, HIT): value decomposition with the textbook codebase — IDQN, VDN and QMIX compared on cooperative Level-Based Foraging and two SMAClite combat scenarios, with rollout videos from early and late training

Zhenhao-Ni /cheese-defender

POMDP cat-and-mouse PettingZoo grid world with recurrent MARL baselines, diagnostics, and demo assets.