Let's get serious...
What I do
I’m a PhD student at Queen Mary University of London. I did the first year of my PhD at University of Essex.
What I’ve done
I studied Software and Computer Engineering at Universidad Autonoma de Madrid (Spain), moved to London and worked as a web developer (in different languages) for a couple of years. I decided to make a change in my career and started the PhD in AI and games.
My interests
My interests include AI, games, automated gameplay, behaviour (player & AI) and heuristics.
For details about my research, refer to Research.
The IGGI programme
I’m one of the students in the Intelligent Games and Games Intelligence (IGGI) programme, which is a fully funded research programme in games, and AI in games, sponsored by EPSRC and possible thanks to the collaboration of four institutions: Queen Mary University of London, University of Essex, Goldsmiths University of London and University of York.
2021
Cristina Guerrero-Romero and Diego Perez-Liebana. “MAP-Elites to Generate a Team of Agents that Elicits Diverse Automated Gameplay”, Proceedings of the 2021 IEEE Conference on Games (CoG), 2021.
Diego Perez-Liebana, Cristina Guerrero-Romero, Alexander Dockhorn, Dominik Jeurissen and Linjie Xu. “Generating Diverse and Competitive Play-Styles for Strategy Games”. Proceedings of the 2021 IEEE Conference on Games (CoG), 2021.
2020
Cristina Guerrero-Romero, Shringi Kumari, Diego Perez-Liebana and Sebastian Deterding. “Studying General Agents in Video Games from the Perspective of Player Experience”, Proceedings of the AAAI Conference on Artificial Intelligence and Interactive Digital Entertainment (AIIDE), 217-223, 2020.
2019
Damien Anderson, Cristina Guerrero-Romero, Diego Perez-Liebana, Philip Rodgers and John Levine, “Ensemble Decision Systems for General Video Game Playing”, Proceedings of the 2019 IEEE Conference on Games (CoG), 1-8, 2019.
2018
Cristina Guerrero-Romero, Simon M Lucas and Diego Perez-Liebana, “Using a Team of General AI Algorithms to Assist Game Design and Testing”, Proceedings of the 2018 IEEE Conference on Computational Intelligence and Games (CIG), 1-8, 2018.
2017
Cristina Guerrero-Romero, Annie Louis and Diego Perez-Liebana, “Beyond Playing to Win: Diversifying Heuristics for GVGAI”, Proceedings of the 2017 IEEE Conference on Computational Intelligence and Games (CIG), 118-125, 2017.
Some of my code - excludes ongoing work, which I have in a private repository until it is mature enough to be shared with the world!
kisenshi.github.io
I use something called Hugo, which is a fantastic static website engine that allows me to have 100% control of the site; precisely what I was looking for. This repository contains the static code once it has been generated to be published. Basically, it’s the site you are visiting at the moment!
Agent Behaviour Research (in GVGAI)
Personalised version of the GVGAI framework that allows providing the heuristic to use in the algorithm at the time of starting the game. This modification allows running the agents with different heuristics (behaviours) without having to update their core code. The heuristics are created in a external file and plugged into the agent during its instantiation. This repository contains the code related to my research in agent behaviour.
It covers the following topics: Heuristic diversification, use of MAP-Elites to generate agents that elicits diverse automated gameplay, and automated gameplay.
Demo: Visualize Diverse Gameplays Based on Agent Behaviour
Interactive tool that allows to visualize the gameplays of agents with different motivations and goals in a same game, by choosing a range of expected stats (features) for each of them. This demo shows the diversity of the team of agents generated for each game and pair of features, eliciting a diverse automated gameplay.
It is possible to see details about the agents generated, play a pre-recorded gameplay of each of them and download an standalone and instructions to run the agents locally.
Agent Behaviour Research - Results Processing
Contains the scripts to process the results and data from the Agent Behaviour Research.
Portal 2D
Game developed using the GVGAI framework (forked into my repository) as assessment for the Game AI Module took at Goldsmiths University in February 2017.
For more details, refer to this blog entrance.
Diversifying Heuristics research (first experiments)
Code for the experiments done in the GVGAI Framework. The experiments are related with heuristic diversification, and the original Framework has been enlarged to add methods to be able to run them, as it was necessary to provide a common ground for the comparison of both the algorithms and the heuristics. These functions are based on the ones already available in the Framework, but allowing to provide the heuristic to be used by the agents separately. Also, the code needed to create heuristic-independent players has been included.
Her Resonance
Game developed in Unity for the Global Game Jam 2017 (#GGJ17) in the 20th-22nd of January 2017.
For more details, refer to this blog entrance.
Hungry Penguins
Game developed in Unity as assessment for the Game Development Module took at Goldsmiths University in November 2016.
For more details, refer to this blog entrance.
Project Euler solutions
Solutions to Project Euler problems. For those who don´t know, Project Euler is an online platform that contains a lot of problems to solve. I like solving problems, and I thought it was a fun way to start using Python and get familiar with the language.
Please note that I publish in here my solutions if you are using the platform I recommend not to spoil yourself, give a try and solve them in your own; where is the fun in using my solutions as yours?
Hackerrank solutions
My solutions to Hackerrank challenges, which is another cool platform with a lot of problems related to algorithms, statistics, machine learning, natural language processing… and contests.
Please try to solve the problems on your own; do not use my solutions as yours, where would be the fun on that?
Code Your Own Adventure
Prototype built with Ruby Sinatra and Bootstrap for the IWDHackathon the weekend of the 7th and 8th of March of 2015. The theme was Make it Happen – Diversity in Tech. The winning solution developed was a storytelling platform to teach children coding basics and encourage them to keep trying until they are able to create the perfect story.
For more details, refer to this blog entrance.
IGGI Conference
September 2018, London, UK
“Using a Team of General AI Algorithms to Assist Game Design and Testing”
IEEE Computational Intelligence and Games (CIG)
August 2018, Maastricht, Netherlands
Presentation of “Using a Team of General AI Algorithms to Assist Game Design and Testing” paper, Session: Vision Papers
IGGI Conference
September 2017, York, UK
“The General Video Game Playing Challenge: Improving RHEA & Playing Beyond Win”, with Raluca D. Gaina.
IEEE Computational Intelligence and Games (CIG)
August 2017, New York, USA
Presentation of “Beyond Playing to Win: Diversifying Heuristics for GVGAI” paper, Special Session on General Video Game AI
2019 IEEE Conference on Games (CoG)
August 2019, London, UK
Webmaster
IGGI Conference
September 2018, London, UK
Workshop chair
For detailed information about my professional experience and education, please refer to my LinkedIn profile.
