143 citations · 546 across the 35 of their papers we have counts for
12 papers · 1 filter
The Time Value of Evolution
Matthew Siper, Ahmed Khalifa, Julian Togelius
In evolutionary search, a weak child can be a valuable ancestor that makes high-fitness regions reachable. Immediate-return control is blind to this delayed utility, penalizing mut…
ELMER: Evolutionary Language Model that Explores and Refines
Matthew Siper, Ahmed Khalifa, Julian Togelius
Program evolution can measure whether a mutation helped, but it rarely controls how far the mutation moves in behavior space. Syntactic edit size is an unreliable proxy: a small co…
Continuous Program Search
Matthew Siper, Muhammad Umair Nasir, Ahmed Khalifa +3
Genetic Programming yields interpretable programs, but small syntactic mutations can induce large, unpredictable behavioral shifts, degrading locality and sample efficiency. We fra…
Lode Enhancer: Level Co-creation Through Scaling
Debosmita Bhaumik, Julian Togelius, Georgios N. Yannakakis +1
We explore AI-powered upscaling as a design assistance tool in the context of creating 2D game levels. Deep neural networks are used to upscale artificially downscaled patches of l…
Lode Encoder: AI-constrained co-creativity
Debosmita Bhaumik, Ahmed Khalifa, Julian Togelius
We present Lode Encoder, a gamified mixed-initiative level creation system for the classic platform-puzzle game Lode Runner. The system is built around several autoencoders which a…
Play with Emotion: Affect-Driven Reinforcement Learning
Matthew Barthet, Ahmed Khalifa, Antonios Liapis +1
This paper introduces a paradigm shift by viewing the task of affect modeling as a reinforcement learning (RL) process. According to the proposed paradigm, RL agents learn a policy…
Path of Destruction: Learning an Iterative Level Generator Using a Small Dataset
Matthew Siper, Ahmed Khalifa, Julian Togelius
We propose a new procedural content generation method which learns iterative level generators from a dataset of existing levels. The Path of Destruction method, as we call it, view…
Learning Controllable Content Generators
Sam Earle, Maria Edwards, Ahmed Khalifa +2
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-spe…
Rotation, Translation, and Cropping for Zero-Shot Generalization
Chang Ye, Ahmed Khalifa, Philip Bontrager +1
Deep Reinforcement Learning (DRL) has shown impressive performance on domains with visual inputs, in particular various games. However, the agent is usually trained on a fixed envi…
PCGRL: Procedural Content Generation via Reinforcement Learning
Ahmed Khalifa, Philip Bontrager, Sam Earle +1
We investigate how reinforcement learning can be used to train level-designing agents. This represents a new approach to procedural content generation in games, where level design…
Superstition in the Network: Deep Reinforcement Learning Plays Deceptive Games
Philip Bontrager, Ahmed Khalifa, Damien Anderson +3
Deep reinforcement learning has learned to play many games well, but failed on others. To better characterize the modes and reasons of failure of deep reinforcement learners, we te…
Illuminating Generalization in Deep Reinforcement Learning through Procedural Level Generation
Niels Justesen, Ruben Rodriguez Torrado, Philip Bontrager +3
Deep reinforcement learning (RL) has shown impressive results in a variety of domains, learning directly from high-dimensional sensory streams. However, when neural networks are tr…