Search Results for author: Christoph Salge

Found 20 papers, 2 papers with code

Skilled motor control implies a low entropy of states but a high entropy of actions

no code implementations22 Dec 2021 Nicola Catenacci Volpi, Martin Greaves, Dari Trendafilov, Christoph Salge, Giovanni Pezzulo, Daniel Polani

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.

Comparing PCG metrics with Human Evaluation in Minecraft Settlement Generation

no code implementations6 Jul 2021 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.

The AI Settlement Generation Challenge in Minecraft: First Year Report

no code implementations27 Mar 2021 Christoph Salge, Michael Cerny Green, Rodrigo Canaan, Filip Skwarski, Rafael Fritsch, Adrian Brightmoore, Shaofang Ye, Changxing Cao, Julian Togelius

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 interesting settlements in Minecraft for an unseen map.

Applications of Artificial Intelligence in Live Action Role-Playing Games (LARP)

no code implementations25 Aug 2020 Christoph Salge, Emily Short, Mike Preuss, Spyridion Samothrakis, Pieter Spronck

Live Action Role-Playing (LARP) games and similar experiences are becoming a popular game genre.

Warmth and Competence to Predict Human Preference of Robot Behavior in Physical Human-Robot Interaction

no code implementations13 Aug 2020 Marcus M. Scheunemann, Raymond H. Cuijpers, Christoph Salge

We found that Warmth and Competence, among all RoSAS and Godspeed dimensions, are the most important predictors for human preferences between different robot behaviors.

Human robot interaction

Human Perception of Intrinsically Motivated Autonomy in Human-Robot Interaction

no code implementations14 Feb 2020 Marcus M. Scheunemann, Christoph Salge, Daniel Polani, Kerstin Dautenhahn

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.

Human robot interaction

Measuring Time with Minimal Clocks

no code implementations17 Jun 2019 Andrei D. Robu, Christoph Salge, Chrystopher L. Nehaniv, Daniel Polani

Clock cascades show a "condensation effect" and the composite clock shows various regimes of markedly different dynamics.

The Riddle of Togelby

no code implementations10 Jun 2019 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 good game.

Automatic Generation of Level Maps with the Do What's Possible Representation

no code implementations23 May 2019 Daniel Ashlock, Christoph Salge

Automatic generation of level maps is a popular form of automatic content generation.

Generative Design in Minecraft: Chronicle Challenge

no code implementations14 May 2019 Christoph Salge, Christian Guckelsberger, Michael Cerny Green, Rodrigo Canaan, Julian Togelius

We introduce the Chronicle Challenge as an optional addition to the Settlement Generation Challenge in Minecraft.

Leveling the Playing Field -- Fairness in AI Versus Human Game Benchmarks

no code implementations17 Mar 2019 Rodrigo Canaan, Christoph Salge, Julian Togelius, Andy Nealen

The extent to which these games benchmark consist of fair competition between human and AI is also a matter of debate.


A Continuous Information Gain Measure to Find the Most Discriminatory Problems for AI Benchmarking

1 code implementation9 Sep 2018 Matthew Stephenson, Damien Anderson, Ahmed Khalifa, John Levine, Jochen Renz, Julian Togelius, Christoph Salge

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.

Expanding the Active Inference Landscape: More Intrinsic Motivations in the Perception-Action Loop

no code implementations21 Jun 2018 Martin Biehl, Christian Guckelsberger, Christoph Salge, Simón C. Smith, Daniel Polani

Research on intrinsic motivations may profit from an additional way to implement intrinsically motivated agents that also share the biological plausibility of active inference.

New And Surprising Ways to Be Mean. Adversarial NPCs with Coupled Empowerment Minimisation

no code implementations4 Jun 2018 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.

Generative Design in Minecraft (GDMC), Settlement Generation Competition

no code implementations27 Mar 2018 Christoph Salge, Michael Cerny Green, Rodrigo Canaan, Julian Togelius

This paper introduces the settlement generation competition for Minecraft, the first part of the Generative Design in Minecraft challenge.

Accelerating Empowerment Computation with UCT Tree Search

no code implementations27 Mar 2018 Christoph Salge, Christian Guckelsberger, Rodrigo Canaan, Tobias Mahlmann

Models of intrinsic motivation present an important means to produce sensible behaviour in the absence of extrinsic rewards.

Changing the Environment Based on Empowerment as Intrinsic Motivation

no code implementations3 Jun 2014 Christoph Salge, Cornelius Glackin, Daniel Polani

In this paper we investigate how the information-theoretic measure of agent empowerment can provide a task-independent, intrinsic motivation to restructure the world.

Decision Making

Changing the Environment based on Intrinsic Motivation

no code implementations14 Oct 2013 Christoph Salge, Daniel Polani

One of the remarkable feats of intelligent life is that it restructures the world it lives in for its own benefit.

Empowerment -- an Introduction

2 code implementations7 Oct 2013 Christoph Salge, Cornelius Glackin, Daniel Polani

This book chapter is an introduction to and an overview of the information-theoretic, task independent utility function "Empowerment", which is defined as the channel capacity between an agent's actions and an agent's sensors.

Cannot find the paper you are looking for? You can Submit a new open access paper.