1 code implementation • 6 May 2021 • Sam Earle, Maria Edwards, Ahmed Khalifa, Philip Bontrager, Julian Togelius
It has recently been shown that reinforcement learning can be used to train generators capable of producing high-quality game levels, with quality defined in terms of some user-specified heuristic.
no code implementations • 20 Feb 2021 • Michael Cerny Green, Ahmed Khalifa, Philip Bontrager, Rodrigo Canaan, Julian Togelius
We present a new concept called Game Mechanic Alignment theory as a way to organize game mechanics through the lens of systemic rewards and agential motivations.
1 code implementation • 12 Feb 2020 • Philip Bontrager, Julian Togelius
Unlike previous approaches to procedural content generation, Generative Playing Networks are end-to-end differentiable and do not require human-designed examples or domain knowledge.
1 code implementation • 27 Jan 2020 • Chang Ye, Ahmed Khalifa, Philip Bontrager, Julian Togelius
Deep Reinforcement Learning (DRL) has shown impressive performance on domains with visual inputs, in particular various games.
6 code implementations • 24 Jan 2020 • Ahmed Khalifa, Philip Bontrager, Sam Earle, Julian Togelius
We investigate how reinforcement learning can be used to train level-designing agents.
no code implementations • 12 Aug 2019 • Philip Bontrager, Ahmed Khalifa, Damien Anderson, Matthew Stephenson, Christoph Salge, Julian Togelius
Deep reinforcement learning has learned to play many games well, but failed on others.
1 code implementation • 28 Jun 2018 • Niels Justesen, Ruben Rodriguez Torrado, Philip Bontrager, Ahmed Khalifa, Julian Togelius, Sebastian Risi
However, when neural networks are trained in a fixed environment, such as a single level in a video game, they will usually overfit and fail to generalize to new levels.
2 code implementations • 6 Jun 2018 • Ruben Rodriguez Torrado, Philip Bontrager, Julian Togelius, Jialin Liu, Diego Perez-Liebana
In this paper, we describe how we interface GVGAI to the OpenAI Gym environment, a widely used way of connecting agents to reinforcement learning problems.
1 code implementation • 24 Jan 2018 • Philip Bontrager, Wending Lin, Julian Togelius, Sebastian Risi
The main insight in this paper is that a GAN trained on a specific target domain can act as a compact and robust genotype-to-phenotype mapping (i. e. most produced phenotypes do resemble valid domain artifacts).
no code implementations • 25 Aug 2017 • Niels Justesen, Philip Bontrager, Julian Togelius, Sebastian Risi
In this article, we review recent Deep Learning advances in the context of how they have been applied to play different types of video games such as first-person shooters, arcade games, and real-time strategy games.
no code implementations • 21 May 2017 • Philip Bontrager, Aditi Roy, Julian Togelius, Nasir Memon, Arun Ross
The proposed method, referred to as Latent Variable Evolution, is based on training a Generative Adversarial Network on a set of real fingerprint images.