Giter Club home page Giter Club logo

smix's Introduction

SMIX(λ)

PyTorch implementation of "SMIX(λ): Enhancing Centralized Value Functions for Cooperative Multi-Agent Reinforcement Learning". If you use our code please cite the paper.

Installation

SMIX(λ) is tested on SMAC environment. The installation procedure is the same as pymarl.

Run SMIX(λ)

Run SMIX(λ) on 3s5z map:

python3 src/main.py --config=smix --env-config=sc2 with env_args.map_name=3s5z

Results

Replays of SMIX(λ)

Videos of SMIX(λ)'s performance on 3s5z scenario are available respectively at:

Citing SMIX(λ)

In BibTeX format:

@inproceedings{wen20smix,
  title={SMIX($\lambda$): Enhancing Centralized Value Functions for Cooperative Multi-Agent Reinforcement Learning},
  author={Wen, Chao and Yao, Xinghu and Wang, Yuhui and Tan, Xiaoyang},
  booktitle={Proceedings of the Thirty-Fourth AAAI Conference on Artificial Intelligence},
  year={2020},
}

smix's People

Contributors

chaovven avatar kabibi avatar mimoralea avatar richardliaw avatar samvelyan avatar tabzraz avatar

Stargazers

 avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar

Watchers

 avatar

smix's Issues

Why there is only one agent in the controller?

Dear chaovven, In https://github.com/chaovven/SMIX/blob/master/src/controllers/basic_controller.py#L75, I found there is only one controller defined here, for homogenous envs, I think it is ok to do so, it is homogenous agents and agents can learn one agent, however, for heterogeneous envs for example 3s5z_vs_3s6z, I think it is not ok to do so since there are ss and zs in each group, right? So, I think there should be defined new agent for each type agent.

How can I calculate the winrate?

Hi, in your paper, I fund there is a winrate metric to evaluate the performance of algorithms. How can I manually calculate the value in StarCraft environment?

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. 📊📈🎉

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google ❤️ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.