Zobrazeno 1 - 10
of 20
pro vyhledávání: '"Palm, Rasmus Berg"'
Biological systems are very robust to morphological damage, but artificial systems (robots) are currently not. In this paper we present a system based on neural cellular automata, in which locomoting robots are evolved and then given the ability to r
Externí odkaz:
http://arxiv.org/abs/2206.06674
Deep generative models can automatically create content of diverse types. However, there are no guarantees that such content will satisfy the criteria necessary to present it to end-users and be functional, e.g. the generated levels could be unsolvab
Externí odkaz:
http://arxiv.org/abs/2206.00106
Autor:
Walker, Kathryn, Palm, Rasmus Berg, Garcia, Rodrigo Moreno, Faina, Andres, Stoy, Kasper, Risi, Sebastian
Materials with the ability to self-classify their own shape have the potential to advance a wide range of engineering applications and industries. Biological systems possess the ability not only to self-reconfigure but also to self-classify themselve
Externí odkaz:
http://arxiv.org/abs/2203.07548
In nature, the process of cellular growth and differentiation has lead to an amazing diversity of organisms -- algae, starfish, giant sequoia, tardigrades, and orcas are all created by the same generative process. Inspired by the incredible diversity
Externí odkaz:
http://arxiv.org/abs/2201.12360
In games, as well as many user-facing systems, adapting content to users' preferences and experience is an important challenge. This paper explores a novel method to realize this goal in the context of dynamic difficulty adjustment (DDA). Here the ai
Externí odkaz:
http://arxiv.org/abs/2105.08484
This paper introduces EvoCraft, a framework for Minecraft designed to study open-ended algorithms. We introduce an API that provides an open-source Python interface for communicating with Minecraft to place and track blocks. In contrast to previous w
Externí odkaz:
http://arxiv.org/abs/2012.04751
Planning is a powerful approach to reinforcement learning with several desirable properties. However, it requires a model of the world, which is not readily available in many real-life problems. In this paper, we propose to learn a world model that e
Externí odkaz:
http://arxiv.org/abs/2011.11293
Hebbian meta-learning has recently shown promise to solve hard reinforcement learning problems, allowing agents to adapt to some degree to changes in the environment. However, because each synapse in these approaches can learn a very specific learnin
Externí odkaz:
http://arxiv.org/abs/2011.06811
Methods for dynamic difficulty adjustment allow games to be tailored to particular players to maximize their engagement. However, current methods often only modify a limited set of game features such as the difficulty of the opponents, or the availab
Externí odkaz:
http://arxiv.org/abs/2005.07677
Publikováno v:
ICDAR 2019
Document information extraction tasks performed by humans create data consisting of a PDF or document image input, and extracted string outputs. This end-to-end data is naturally consumed and produced when performing the task because it is valuable i
Externí odkaz:
http://arxiv.org/abs/1812.07248