AI Rank
EN
← 开源
Lizhi-sjtu

MARL-code-pytorch

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

Model DevelopmentReinforcement LearningPython
在 GitHub 打开
增长势头
+024 小时新增 Star0.0%
744
Star
82
Fork
+1
本周
1
贡献者
创建于 2022-05-17 · 更新于 2026-10-13 · 今日第 14296 名
主要开发者
Lizhi-sjtu

Lizhi-sjtu/MARL-code-pytorch 排名第 14,296，有 744 个星标。

同类别比较

Lizhi-sjtu/MARL-code-pytorch 排名第 14,296，此处有 8 个同类条目；ilivans/tf-rnn-attention 排名第 14,299。

同类别比较
名称排名指标
arcprize/ARC-AGI-214,283
星标数:
745
分叉数:
119
asyml/texar-pytorch14,284
语言:
Python
星标数:
745
分叉数:
111
简介:
Integrating the Best of TF into PyTorch, for Machine Learning, Natural Language Processing, and Text Generation. This is part of the CASL project: http://casl-project.ai/
knuddelsgmbh/jtokkit14,288
语言:
Java
星标数:
745
分叉数:
52
简介:
JTokkit is a Java tokenizer library designed for use with OpenAI models.
songlab-cal/tape14,292
语言:
Python
星标数:
745
分叉数:
134
简介:
Tasks Assessing Protein Embeddings (TAPE), a set of five biologically relevant semi-supervised learning tasks spread across different domains of protein biology.
ilivans/tf-rnn-attention14,299
语言:
Python
星标数:
744
分叉数:
288
简介:
Tensorflow implementation of attention mechanism for text classification tasks.
Linesight-RL/linesight14,303
语言:
Python
星标数:
743
分叉数:
70
简介:
AI Plays Trackmania with Reinforcement Learning
MisaOgura/flashtorch14,304
语言:
HTML
星标数:
743
分叉数:
86
bubbliiiing/ssd-pytorch14,309
语言:
Python
星标数:
743
分叉数:
172
简介:
这是一个ssd-pytorch的源码，可以用于训练自己的模型。
关键参数与规格
关键参数与规格
参数值
语言Python
类别Model Development
子类别Reinforcement Learning
关键词RL
星标数744
分叉数82
贡献者1
创建日期2022-05-17
更新日期2026-10-13
1 天星标数0
7 天星标数1
排名14,296
上次排名14,152
排名变化-144
7 天星标排名10,774
上次 7 天星标排名10,833
7 天星标排名变化59
总星标排名14,174
上次总星标排名14,148
总星标排名变化-26
国家China
README 摘录

MARL-code-pytorch Concise pytorch implements of MARL algorithms, including MAPPO, MADDPG, MATD3, QMIX and VDN. 5 Multi-Agent Particle-World Environment(MPE) SMAC-StarCraft Multi-Agent Challenge Trainning results 1. MADDPG and MATD3 in MPE (continuous action space) Some Details In order to facilitate switching between discrete action space and continuous action space in MPE environments, we make some small modifications in MPE source code. py We add an argument named 'discrete' in 'make_env. py We also add

an argument named 'discrete' in 'environment. If your want to use discrete action space mode, you can use 'env=make_env(scenario_name, discrete=True)' If your want to use continuous action space mode, you can use 'env=make_env(scenario_name, discrete=False)'

常见问题

记录了多少星标和分叉？

Lizhi-sjtu/MARL-code-pytorch 有 744 个星标和 82 个分叉。

仓库排名是多少？

Lizhi-sjtu/MARL-code-pytorch 排名第 14,296。

记录的语言和类别是什么？

Lizhi-sjtu/MARL-code-pytorch 有 744 个星标，语言为 Python，类别为 Model Development。

哪个仓库排名最接近？

Lizhi-sjtu/MARL-code-pytorch 与 ilivans/tf-rnn-attention 比较，后者排名第 14,299，有 744 个星标。

README

MARL-code-pytorch

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

Requirements

python==3.7.9

numpy==1.19.4

pytorch==1.5.0

tensorboard==0.6.0

gym==0.10.5

Multi-Agent Particle-World Environment(MPE)

SMAC-StarCraft Multi-Agent Challenge

Trainning results

1. MAPPO in MPE (discrete action space)

2. MAPPO in StarCraft II(SMAC)

3. QMIX and VDN in StarCraft II(SMAC)

4. MADDPG and MATD3 in MPE (continuous action space)

Some Details

In order to facilitate switching between discrete action space and continuous action space in MPE environments, we make some small modifications in MPE source code.

1. make_env.py

We add an argument named 'discrete' in 'make_env.py',which is a bool variable.

2. environment.py

We also add an argument named 'discrete' in 'environment.py'.

3. How to create a MPE environment?

If your want to use discrete action space mode, you can use 'env=make_env(scenario_name, discrete=True)'

If your want to use continuous action space mode, you can use 'env=make_env(scenario_name, discrete=False)'

排名相邻
同类项目