Data

Tools

Indexes

Applications

Experiments

Open Source Science

nn_bimatrix_games

https://github.com/massimilianofurlan/nn_bimatrix_games

Science Score: 54.0%

This score indicates how likely this project is to be science-related based on various indicators:

  • ✓
    CITATION.cff file
    Found CITATION.cff file
  • ✓
    codemeta.json file
    Found codemeta.json file
  • ✓
    .zenodo.json file
    Found .zenodo.json file
  • ○
    DOI references
  • ✓
    Academic publication links
    Links to: arxiv.org
  • ○
    Academic email domains
  • ○
    Institutional organization owner
  • ○
    JOSS paper metadata
  • ○
    Scientific vocabulary similarity
    Low similarity (11.2%) to scientific vocabulary
Last synced: 6 months ago · JSON representation ·

Repository

Basic Info
  • Host: GitHub
  • Owner: massimilianofurlan
  • License: gpl-3.0
  • Language: Python
  • Default Branch: main
  • Size: 190 KB
Statistics
  • Stars: 0
  • Watchers: 1
  • Forks: 0
  • Open Issues: 0
  • Releases: 0
Created about 1 year ago · Last pushed 10 months ago
Metadata Files
Readme License Citation

README.md

Overview

This repository contains the code for "D. Condorelli, M. Furlan. Deep Learning to Play Games".

Replication instructions are listed in the replication file. This is a work in progress. Replication instructions might be broken.

Table of Contents

Installation (one-time setup)

Follow these steps to set up the project environment. You only need to do this once:

  1. Clone the Repository:
    Download the code to your local machine:

    bash git clone https://github.com/massimilianofurlan/nn_bimatrix_games.git

  2. Install Python:
    Make sure Python is installed. On macOS, you can use Homebrew:

    bash brew install python3.12

  3. Set Up a Virtual Environment:
    Navigate to the project folder and create a virtual environment:

    bash cd nn_bimatrix_games python3.12 -m venv venv

  4. Activate the Virtual Environment:
    Activate the environment to isolate project dependencies:

    bash source venv/bin/activate

  5. Install Dependencies:
    Upgrade pip and install the required libraries:

    bash pip install --upgrade pip pip install -r requirements.txt

Once these steps are completed, the environment is ready for use.

Basic Usage

Make sure you are in the nn_bimatrix_games project folder and the virtual environment is activated:

bash cd nn_bimatrix_games source venv/bin/activate

(a) Launching Training

To train a pair of neural networks on 2×2 games, use the following command:

bash python -m src.scripts.training.train --config=2x2_example --batch_size=128 --n_games=33554432 --name=2x2_example

(b) Generating an Evaluation Set

To generate a labeled dataset for evaluating 2×2 games:

bash python -m src.scripts.data.generate_evalset --n_actions=2 --n_games=131072 --name=2x2_example_dataset

(c) Evaluating the Model on the Evaluation Set

To evaluate a trained model on the evaluation dataset:

bash python -m src.scripts.evaluation.evaluate --model=2x2_example --dataset=2x2_example_dataset

Note: Make sure that the --model and --dataset names match the names used during training and evaluation set generation.

License

This project is licensed under the MIT License. See the LICENSE file for details.

Owner

  • Name: Massimiliano Furlan
  • Login: massimilianofurlan
  • Kind: user
  • Location: Coventry, United Kingdom
  • Company: University of Warwick

MRes in Economics

Citation (CITATION.cff) 

cff-version: 1.2.0
message: "If you use this software, please cite it as below."
authors:
  - family-names: "Condorelli"
    given-names: "Daniele"
  - family-names: "Furlan"
    given-names: "Massimiliano"
title: "Deep Learning to Play Games"
version: 1.0.0
date-released: 2023-09-25
url: "https://github.com/massimilianofurlan/nn_bimatrix_games"
repository: "https://github.com/massimilianofurlan/nn_bimatrix_games"

GitHub Events

Total
  • Delete event: 1
  • Public event: 1
  • Push event: 36
  • Create event: 1
Last Year
  • Delete event: 1
  • Public event: 1
  • Push event: 36
  • Create event: 1