216 citations · 396 across the 26 of their papers we have counts for
31 papers
Exploring Minecraft Settlement Generators with Generative Shift Analysis
Jean-Baptiste Hervé, Oliver Withington, Marion Hervé +2
With growing interest in Procedural Content Generation (PCG) it becomes increasingly important to develop methods and tools for evaluating and comparing alternative systems. There…
The Effect of Noise on the Emergence of Continuous Norms and its Evolutionary Dynamics
Stavros Anagnou, Daniel Polani, Christoph Salge
We examine the effect of noise on societies of agents using an agent-based model of evolutionary norm emergence. Generally, we see that noisy societies are more selfish, smaller an…
Automated Isovist Computation for Minecraft
Jean-Baptiste Hervé, Christoph Salge
Procedural content generation for games is a growing trend in both research and industry, even though there is no consensus of how good content looks, nor how to automatically eval…
Reliably Re-Acting to Partner's Actions with the Social Intrinsic Motivation of Transfer Empowerment
Tessa van der Heiden, Herke van Hoof, Efstratios Gavves +1
We consider multi-agent reinforcement learning (MARL) for cooperative communication and coordination tasks. MARL agents can be brittle because they can overfit their training partn…
Skilled motor control implies a low entropy of states but a high entropy of actions
Nicola Catenacci Volpi, Martin Greaves, Dari Trendafilov +3
The mastery of skills such as playing tennis or balancing an inverted pendulum implies a very accurate control of movements to achieve the task goals. Traditional accounts of skill…
Impressions of the GDMC AI Settlement Generation Challenge in Minecraft
Christoph Salge, Claus Aranha, Adrian Brightmoore +15
The GDMC AI settlement generation challenge is a PCG competition about producing an algorithm that can create an "interesting" Minecraft settlement for a given map. This paper cont…
Comparing PCG metrics with Human Evaluation in Minecraft Settlement Generation
Jean-Baptiste Hervé, Christoph Salge
There are a range of metrics that can be applied to the artifacts produced by procedural content generation, and several of them come with qualitative claims. In this paper, we ada…
The AI Settlement Generation Challenge in Minecraft: First Year Report
Christoph Salge, Michael Cerny Green, Rodrigo Canaan +6
This article outlines what we learned from the first year of the AI Settlement Generation Competition in Minecraft, a competition about producing AI programs that can generate inte…
Robust Multi-Agent Reinforcement Learning with Social Empowerment for Coordination and Communication
T. van der Heiden, C. Salge, E. Gavves +1
We consider the problem of robust multi-agent reinforcement learning (MARL) for cooperative communication and coordination tasks. MARL agents, mainly those trained in a centralized…
Warmth and Competence to Predict Human Preference of Robot Behavior in Physical Human-Robot Interaction
Marcus M. Scheunemann, Raymond H. Cuijpers, Christoph Salge
A solid methodology to understand human perception and preferences in human-robot interaction (HRI) is crucial in designing real-world HRI. Social cognition posits that the dimensi…
Human Perception of Intrinsically Motivated Autonomy in Human-Robot Interaction
Marcus M. Scheunemann, Christoph Salge, Daniel Polani +1
A challenge in using robots in human-inhabited environments is to design behavior that is engaging, yet robust to the perturbations induced by human interaction. Our idea is to imb…
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…
Measuring Time with Minimal Clocks
Andrei D. Robu, Christoph Salge, Chrystopher L. Nehaniv +1
Being able to measure time, whether directly or indirectly, is a significant advantage for an organism. It allows for the timely reaction to regular or predicted events, reducing t…
Organic Building Generation in Minecraft
Michael Cerny Green, Christoph Salge, Julian Togelius
This paper presents a method for generating floor plans for structures in Minecraft (Mojang 2009). Given a 3D space, it will auto-generate a building to fill that space using a com…
The Riddle of Togelby
Daniel Ashlock, Christoph Salge
At the 2017 Artificial and Computational Intelligence in Games meeting at Dagstuhl, Julian Togelius asked how to make spaces where every way of filling in the details yielded a goo…
Automatic Generation of Level Maps with the Do What's Possible Representation
Daniel Ashlock, Christoph Salge
Automatic generation of level maps is a popular form of automatic content generation. In this study, a recently developed technique employing the {\em do what's possible} represent…
Generative Design in Minecraft: Chronicle Challenge
Christoph Salge, Christian Guckelsberger, Michael Cerny Green +2
We introduce the Chronicle Challenge as an optional addition to the Settlement Generation Challenge in Minecraft. One of the foci of the overall competition is adaptive procedural…
Intrinsically Motivated Autonomy in Human-Robot Interaction: Human Perception of Predictive Information in Robots
Marcus M. Scheunemann, Christoph Salge, Kerstin Dautenhahn
In this paper we present a fully autonomous and intrinsically motivated robot usable for HRI experiments. We argue that an intrinsically motivated approach based on the Predictive…
Leveling the Playing Field -- Fairness in AI Versus Human Game Benchmarks
Rodrigo Canaan, Christoph Salge, Julian Togelius +1
From the beginning if the history of AI, there has been interest in games as a platform of research. As the field developed, human-level competence in complex games became a target…
A Continuous Information Gain Measure to Find the Most Discriminatory Problems for AI Benchmarking
Matthew Stephenson, Damien Anderson, Ahmed Khalifa +4
This paper introduces an information-theoretic method for selecting a subset of problems which gives the most information about a group of problem-solving algorithms. This method w…
Expanding the Active Inference Landscape: More Intrinsic Motivations in the Perception-Action Loop
Martin Biehl, Christian Guckelsberger, Christoph Salge +2
Active inference is an ambitious theory that treats perception, inference and action selection of autonomous agents under the heading of a single principle. It suggests biologicall…
New And Surprising Ways to Be Mean. Adversarial NPCs with Coupled Empowerment Minimisation
Christian Guckelsberger, Christoph Salge, Julian Togelius
Creating Non-Player Characters (NPCs) that can react robustly to unforeseen player behaviour or novel game content is difficult and time-consuming. This hinders the design of belie…
Accelerating Empowerment Computation with UCT Tree Search
Christoph Salge, Christian Guckelsberger, Rodrigo Canaan +1
Models of intrinsic motivation present an important means to produce sensible behaviour in the absence of extrinsic rewards. Applications in video games are varied, and range from…
Generative Design in Minecraft (GDMC), Settlement Generation Competition
Christoph Salge, Michael Cerny Green, Rodrigo Canaan +1
This paper introduces the settlement generation competition for Minecraft, the first part of the Generative Design in Minecraft challenge. The settlement generation competition is…