qmix ├── README_CN. md # 说明文档 ├── ascend_310_infer │ ├── inc │ │ ├── utils. h │ ├── src │ │ ├── utils. cc │ │ ├── main. cc # Ascend 310 cpp模型文件 │ ├── build. sh # 编译脚本 │ ├── CMakeLists. txt # C++过程文件 ├── scripts │ ├── run ...

2010年2月4日 · QMIX: QMIX: Monotonic Value Function Factorisation for Deep Multi-Agent Reinforcement Learning; COMA: Counterfactual Multi-Agent Policy Gradients; VDN: Value-Decomposition Networks For Cooperative Multi-Agent Learning; IQL: Independent Q-Learning; QTRAN: QTRAN: Learning to Factorize with Transformation for Cooperative Multi-Agent …

Qmix模型在星际争霸2（StarCraft Ⅱ）的环境下进行强化学习训练。 一个智能体控制一个单位，智能体的行为空间为移动、攻击、停止和无操作，奖励由总伤害加上击杀10分加上团灭200分组成。

2022.10.10 update: add qmix_high_sample_efficiency.yaml, which uses 4 processes for training, slower but higher sample efficiency. 2021.10.28 update: add Google Football Environments [vdn_gfootball.yaml] (use `simple115 features`). 2021.10.4 update: add QMIX with attention (qmix_att.yaml) as a baseline for Communication tasks.

PyTorch implementation of Soft Actor-Critic (SAC), Twin Delayed DDPG (TD3), Actor-Critic (AC/A2C), Proximal Policy Optimization (PPO), QT-Opt, PointNet..

@inproceedings{rashid2020weighted, title={Weighted QMIX: Expanding Monotonic Value Function Factorisation}, author={Rashid, Tabish and Farquhar, Gregory and Peng, Bei and Whiteson, Shimon}, booktitle={Advances in Neural Information Processing Systems}, year={2020} }

在ma_gym环境复现强化学的COMA Qmix和自己改进的代码（In the MA_GYM environment to reproduce the enhanced COMA Qmix and their own improved code） 网络均使用pytorch搭建。python版本3.6。(Pytorch is used for all networks.

Implementation of the QMIX using Pytorch. Contribute to dodoseung/qmix-pytorch development by creating an account on GitHub.

The MARL baselines include independence learning (IQL, A2C, DDPG, TRPO, PPO), centralized critic learning (COMA, MADDPG, MAPPO, HATRPO), and value decomposition (QMIX, VDN, FACMAC, VDA2C) are all implemented. Popular environments like SMAC, MaMujoco, and Google Research Football are provided with a unified interface.

Migrated QMIX networks from Pytorch to Tensorflow 2.0. - yunanyan/Starcraft-QMIX-with-Tensorflow-2.0.