AI Rank
中文
← Open Source
Lizhi-sjtu

MARL-code-pytorch

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

Model DevelopmentReinforcement LearningPython
Open on GitHub
Momentum
+0stars in 24 hours0.0%
744
Stars
82
Forks
+1
This week
1
Contributors
Created 2022-05-17 · Updated 2026-10-13 · #14296 today
Top developers
Lizhi-sjtu

Lizhi-sjtu/MARL-code-pytorch is ranked 14,296 with 744 stars.

Same-category comparison

Lizhi-sjtu/MARL-code-pytorch is ranked 14,296 among these 8 peers; ilivans/tf-rnn-attention is ranked 14,299.

Same-category comparison
NameRankMetrics
arcprize/ARC-AGI-214,283
Stars:
745
Forks:
119
asyml/texar-pytorch14,284
Language:
Python
Stars:
745
Forks:
111
Description:
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
Language:
Java
Stars:
745
Forks:
52
Description:
JTokkit is a Java tokenizer library designed for use with OpenAI models.
songlab-cal/tape14,292
Language:
Python
Stars:
745
Forks:
134
Description:
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
Language:
Python
Stars:
744
Forks:
288
Description:
Tensorflow implementation of attention mechanism for text classification tasks.
Linesight-RL/linesight14,303
Language:
Python
Stars:
743
Forks:
70
Description:
AI Plays Trackmania with Reinforcement Learning.
MisaOgura/flashtorch14,304
Language:
HTML
Stars:
743
Forks:
86
bubbliiiing/ssd-pytorch14,309
Language:
Python
Stars:
743
Forks:
172
Key parameters and specifications
Key parameters and specifications
ParameterValue
LanguagePython
CategoryModel Development
SubcategoryReinforcement Learning
KeywordsRL
Stars744
Forks82
Contributors1
Created date2022-05-17
Updated date2026-10-13
Stars in 1 day0
Stars in 7 days1
Rank14,296
Previous rank14,152
Rank change-144
7-day stars rank10,774
Previous 7-day stars rank10,833
7-day stars rank change59
Total stars rank14,174
Previous total stars rank14,148
Total stars rank change-26
CountryChina
README summary

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)'

Frequently asked questions

How many stars and forks are recorded?

Lizhi-sjtu/MARL-code-pytorch has 744 stars and 82 forks.

What is the repository rank?

Lizhi-sjtu/MARL-code-pytorch is ranked 14,296.

What language and category are recorded?

Lizhi-sjtu/MARL-code-pytorch has 744 stars, uses Python and belongs to Model Development.

Which repository is closest in rank?

Lizhi-sjtu/MARL-code-pytorch is compared with ilivans/tf-rnn-attention, ranked 14,299 with 744 stars.

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)'

Nearby in the ranking
Similar items