Zobrazeno 1 - 10
of 47
pro vyhledávání: '"Christoph Salge"'
Autor:
Nicola Catenacci Volpi, Martin Greaves, Dari Trendafilov, Christoph Salge, Giovanni Pezzulo, Daniel Polani
Publikováno v:
PLoS Computational Biology, Vol 19, Iss 1, p e1010810 (2023)
The mastery of skills, such as balancing an inverted pendulum, implies a very accurate control of movements to achieve the task goals. Traditional accounts of skilled action control that focus on either routinization or perceptual control make opposi
Externí odkaz:
https://doaj.org/article/786ad5fb834a411596bad8660d7242f0
Publikováno v:
Frontiers in Neurorobotics, Vol 12 (2018)
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 biologically plausible explanations for many cognitive phenomena, including cons
Externí odkaz:
https://doaj.org/article/0b1f53e66acb4a06a0348144dead1105
Autor:
Christoph Salge, Daniel Polani
Publikováno v:
Frontiers in Robotics and AI, Vol 4 (2017)
The greater ubiquity of robots creates a need for generic guidelines for robot behavior. We focus less on how a robot can technically achieve a predefined goal and more on what a robot should do in the first place. Particularly, we are interested in
Externí odkaz:
https://doaj.org/article/41f6c1559d654e799629645c70348b53
Publikováno v:
Entropy, Vol 16, Iss 5, Pp 2789-2819 (2014)
One aspect of intelligence is the ability to restructure your own environment so that the world you live in becomes more beneficial to you. In this paper we investigate how the information-theoretic measure of agent empowerment can provide a task-ind
Externí odkaz:
https://doaj.org/article/3a318ebaf57d4493839312061cdfd78a
Publikováno v:
PLoS ONE, Vol 10, Iss 10, p e0139475 (2015)
We propose a model that explains the reliable emergence of power laws (e.g., Zipf's law) during the development of different human languages. The model incorporates the principle of least effort in communications, minimizing a combination of the info
Externí odkaz:
https://doaj.org/article/4217addad69f4510a9f4df233108e30a
Publikováno v:
IEEE Transactions on Games. 14:539-542
Game content has long been created using procedural generation. However, many of these systems are currently designed in an ad-hoc manner, and there is a lack of knowledge around the design criteria that lead to generators producing the most successf
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::369b5e33dbab3c3593efbf9debfb73ac
https://doi.org/10.36227/techrxiv.22698484.v1
https://doi.org/10.36227/techrxiv.22698484.v1
Autor:
Christoph Salge, Claus Aranha, Adrian Brightmoore, Sean Butler, Rodrigo De Moura Canaan, Michael Cook, Michael Green, Hagen Fischer, Christian Guckelsberger, Jupiter Hadley, Jean-Baptiste Herve, Mark Johnson, Quinn Kybartas, David Mason, Mike Preuss, Tristan Smith, Ruck Thawonmas, Julian Togelius
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 contains a collection of written experiences with this competition, by par
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::a27b07755024453ccb1ce88fd98438d0
http://arxiv.org/abs/2108.02955
http://arxiv.org/abs/2108.02955
Autor:
Jean-Baptiste Hervé, Christoph Salge
Publikováno v:
FDG
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 adapt a range of existing PCG metrics to generated Minecraft settlements,
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::7254b984102b69442d2535f14d16d99c
Autor:
Shaofang Ye, Julian Togelius, Rodrigo Canaan, Changxing Cao, Filip Skwarski, Rafael Fritsch, Michael Cerny Green, Adrian Brightmoore, Christoph Salge
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. This challenge see
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::382df95811e64c4af7e4100e66b624bd