Giter VIP home page Giter VIP logo

seac's Introduction

Shared Experience Actor Critic

This repository is the official implementation of Shared Experience Actor Critic.

Requirements

For the experiments in LBF and RWARE, please install from:

Also requires, PyTorch 1.6+

Training - SEAC

To train the agents in the paper, navigate to the seac directory:

cd seac

And run:

python train.py with <env config>

Valid environment configs are:

  • env_name=Foraging-15x15-3p-4f-v0 time_limit=25
  • ...
  • env_name=Foraging-12x12-2p-1f-v0 time_limit=25 or any other foraging environment size/configuration.
  • env_name=rware-tiny-2ag-v1 time_limit=500
  • env_name=rware-tiny-4ag-v1 time_limit=500
  • ...
  • env_name=rware-tiny-2ag-hard-v1 time_limit=500 or any other rware environment size/configuration.

Training - SEQL

To train the agents in the paper, navigate to the seac directory:

cd seql

And run the training script. Possible options are:

  • python lbf_train.py --env Foraging-12x12-2p-1f-v0
  • ...
  • python lbf_train.py --env Foraging-15x15-3p-4f-v0 or any other foraging environment size/configuration.
  • python rware_train.py --env "rware-tiny-2ag-v1"
  • ...
  • python rware_train.py --env "rware-tiny-4ag-v1"or any other rware environment size/configuration.

Evaluation/Visualization - SEAC

To load and render the pretrained models in SEAC, run in the seac directory

python evaluate.py

Citation

@inproceedings{christianos2020shared,
  title={Shared Experience Actor-Critic for Multi-Agent Reinforcement Learning},
  author={Christianos, Filippos and Sch{\"a}fer, Lukas and Albrecht, Stefano V},
  booktitle = {Advances in Neural Information Processing Systems},
  year={2020}
}

seac's People

Contributors

semitable avatar lukasschaefer avatar

Recommend Projects

  • React photo React

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

  • Vue.js photo Vue.js

    ๐Ÿ–– 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. ๐Ÿ“Š๐Ÿ“ˆ๐ŸŽ‰

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 โค๏ธ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.