Skip to content
IJCAI 2019 - Regularized Opponent Model with Maximum Entropy Objective (ROMMEO)
Python
Branch: master
Clone or download
Permalink
Type Name Latest commit message Commit time
Failed to load latest commit information.
experiment Init commit for code Feb 24, 2019
maci Init commit for code Feb 24, 2019
.gitignore Init commit for code Feb 24, 2019
README.md Update README.md Aug 19, 2019
ROMMEO_Appendix.pdf Added appendix, slides, poster Aug 19, 2019
ROMMEO_Poster.pdf Added appendix, slides, poster Aug 19, 2019
ROMMEO_Slides.pdf Add files via upload Aug 19, 2019
requirements.txt Init commit for code Feb 24, 2019
setup.py Init commit for code Feb 24, 2019

README.md

Regularized Opponent Model with Maximum Entropy Objective

This repo aims to provide an algorithm implementation for IJCAI 2019 paper Regularized Opponent Model with Maximum Entropy Objective (ROMMEO) and its baselines.

There are some additional materials avaiable here:

Installation

  1. Clone rllrb
cd <installation_path_of_your_choice>
git clone https://github.com/rll/rllab.git
cd rllab
git checkout b3a28992eca103cab3cb58363dd7a4bb07f250a0
sudo pip3 install -e .
  1. Intsall other dependencies
sudo pip3 install joblib,path.py,gtimer,theano,keras,tensorflow,gym, tensorflow_probability
  1. Intsall maci
cd maci
sudo pip3 install -e .

Runing Experiments

cd experiment
python3 run_rommeo.py
python3 run_baseline.py
You can’t perform that action at this time.