Search Results for author: Sebastian Risi

Found 60 papers, 28 papers with code

Towards Self-Assembling Artificial Neural Networks through Neural Developmental Programs

no code implementations17 Jul 2023 Elias Najarro, Shyam Sudhakaran, Sebastian Risi

Biological nervous systems are created in a fundamentally different way than current artificial neural networks.

Offline RL

CLIPMasterPrints: Fooling Contrastive Language-Image Pre-training Using Latent Variable Evolution

1 code implementation7 Jul 2023 Matthias Freiberger, Peter Kun, Anders Sundnes Løvlie, Sebastian Risi

We investigate the properties of the mined fooling master images, and find that images trained on a small number of image captions potentially generalize to a much larger number of semantically related captions.

Image Captioning

Learning to Act through Evolution of Neural Diversity in Random Neural Networks

no code implementations25 May 2023 Joachim Winther Pedersen, Sebastian Risi

Biological nervous systems consist of networks of diverse, sophisticated information processors in the form of neurons of different classes.

MarioGPT: Open-Ended Text2Level Generation through Large Language Models

1 code implementation12 Feb 2023 Shyam Sudhakaran, Miguel González-Duque, Claire Glanois, Matthias Freiberger, Elias Najarro, Sebastian Risi

Procedural Content Generation (PCG) algorithms provide a technique to generate complex and diverse environments in an automated way.

Skill Decision Transformer

no code implementations31 Jan 2023 Shyam Sudhakaran, Sebastian Risi

However many of these methods only optimize for high returns, and may not extract much information from a diverse dataset of trajectories.

D4RL Descriptive +2

Severe Damage Recovery in Evolving Soft Robots through Differentiable Programming

no code implementations14 Jun 2022 Kazuya Horibe, Kathryn Walker, Rasmus Berg Palm, Shyam Sudhakaran, Sebastian Risi

Biological systems are very robust to morphological damage, but artificial systems (robots) are currently not.

Minimal Neural Network Models for Permutation Invariant Agents

no code implementations12 May 2022 Joachim Winther Pedersen, Sebastian Risi

Organisms in nature have evolved to exhibit flexibility in face of changes to the environment and/or to themselves.

Goal-Guided Neural Cellular Automata: Learning to Control Self-Organising Systems

1 code implementation25 Apr 2022 Shyam Sudhakaran, Elias Najarro, Sebastian Risi

Inspired by cellular growth and self-organization, Neural Cellular Automata (NCAs) have been capable of "growing" artificial cells into images, 3D structures, and even functional machines.

HyperNCA: Growing Developmental Networks with Neural Cellular Automata

1 code implementation25 Apr 2022 Elias Najarro, Shyam Sudhakaran, Claire Glanois, Sebastian Risi

In contrast to deep reinforcement learning agents, biological neural networks are grown through a self-organized developmental process.

reinforcement-learning Reinforcement Learning (RL)

A Unified Substrate for Body-Brain Co-evolution

1 code implementation22 Mar 2022 Sidney Pontes-Filho, Kathryn Walker, Elias Najarro, Stefano Nichele, Sebastian Risi

The genome of such a multicellular organism guides the development of its body from a single cell, including its control system.

Physical Neural Cellular Automata for 2D Shape Classification

1 code implementation14 Mar 2022 Kathryn Walker, Rasmus Berg Palm, Rodrigo Moreno Garcia, Andres Faina, Kasper Stoy, Sebastian Risi

Materials with the ability to self-classify their own shape have the potential to advance a wide range of engineering applications and industries.


Variational Neural Cellular Automata

1 code implementation ICLR 2022 Rasmus Berg Palm, Miguel González-Duque, Shyam Sudhakaran, Sebastian Risi

Additionally, we show that the VNCA can learn a distribution of stable attractors that can recover from significant damage.

Safer Reinforcement Learning through Transferable Instinct Networks

1 code implementation14 Jul 2021 Djordje Grbic, Sebastian Risi

Random exploration is one of the main mechanisms through which reinforcement learning (RL) finds well-performing policies.

reinforcement-learning Reinforcement Learning (RL)

Dealing with Adversarial Player Strategies in the Neural Network Game iNNk through Ensemble Learning

no code implementations5 Jul 2021 Mathias Löwe, Jennifer Villareale, Evan Freed, Aleksanteri Sladek, Jichen Zhu, Sebastian Risi

In this paper, we focus on the adversarial player strategy aspect in the game iNNk, in which players try to communicate secret code words through drawings with the goal of not being deciphered by a NN.

Ensemble Learning Transfer Learning

Hybrid Encoding For Generating Large Scale Game Level Patterns With Local Variations

2 code implementations27 May 2021 Jacob Schrum, Benjamin Capps, Kirby Steckel, Vanessa Volz, Sebastian Risi

However, collections of latent vectors can also be evolved directly, producing more chaotic levels.

Fast Game Content Adaptation Through Bayesian-based Player Modelling

no code implementations18 May 2021 Miguel González-Duque, Rasmus Berg Palm, Sebastian Risi

Current systems for DDA rely on expensive data mining, or on hand-crafted rules designed for particular domains, and usually adapts to keep players in the flow, leaving no room for the designer to present content that is purposefully easy or difficult.

Evolving and Merging Hebbian Learning Rules: Increasing Generalization by Decreasing the Number of Rules

no code implementations16 Apr 2021 Joachim Winther Pedersen, Sebastian Risi

Inspired by the biological phenomenon of the genomic bottleneck, we show that by allowing multiple connections in the network to share the same local learning rule, it is possible to drastically reduce the number of trainable parameters, while obtaining a more robust agent.


Rapid Risk Minimization with Bayesian Models Through Deep Learning Approximation

no code implementations29 Mar 2021 Mathias Löwe, Per Lunnemann Hansen, Sebastian Risi

For a BM, making predictions with the lowest expected loss requires integrating over the posterior distribution.

Active Learning

Growing 3D Artefacts and Functional Machines with Neural Cellular Automata

1 code implementation15 Mar 2021 Shyam Sudhakaran, Djordje Grbic, Siyan Li, Adam Katona, Elias Najarro, Claire Glanois, Sebastian Risi

Neural Cellular Automata (NCAs) have been proven effective in simulating morphogenetic processes, the continuous construction of complex structures from very few starting cells.

Improving Object Detection in Art Images Using Only Style Transfer

1 code implementation12 Feb 2021 David Kadish, Sebastian Risi, Anders Sundnes Løvlie

We generate a large dataset for training and validation by modifying the images in the COCO dataset using AdaIn style transfer.

object-detection Object Detection +2

Regenerating Soft Robots through Neural Cellular Automata

1 code implementation4 Feb 2021 Kazuya Horibe, Kathryn Walker, Sebastian Risi

Our approach allows simulated soft robots that are damaged to partially regenerate their original morphology through local cell interactions alone and regain some of their ability to locomote.

Player-AI Interaction: What Neural Network Games Reveal About AI as Play

no code implementations15 Jan 2021 Jichen Zhu, Jennifer Villareale, Nithesh Javvaji, Sebastian Risi, Mathias Löwe, Rush Weigelt, Casper Harteveld

The advent of artificial intelligence (AI) and machine learning (ML) bring human-AI interaction to the forefront of HCI research.

EvoCraft: A New Challenge for Open-Endedness

1 code implementation8 Dec 2020 Djordje Grbic, Rasmus Berg Palm, Elias Najarro, Claire Glanois, Sebastian Risi

In contrast to previous work in Minecraft that focused on learning to play the game, the grand challenge we pose here is to automatically search for increasingly complex artifacts in an open-ended fashion.

Testing the Genomic Bottleneck Hypothesis in Hebbian Meta-Learning

1 code implementation13 Nov 2020 Rasmus Berg Palm, Elias Najarro, Sebastian Risi

We test this hypothesis by decoupling the number of Hebbian learning rules from the number of synapses and systematically varying the number of Hebbian learning rules.

Clustering Meta-Learning

The power of pictures: using ML assisted image generation to engage the crowd in complex socioscientific problems

no code implementations15 Oct 2020 Janet Rafner, Lotte Philipsen, Sebastian Risi, Joel Simon, Jacob Sherson

Human-computer image generation using Generative Adversarial Networks (GANs) is becoming a well-established methodology for casual entertainment and open artistic exploration.

Image Generation

Deep Learning for Procedural Content Generation

no code implementations9 Oct 2020 Jialin Liu, Sam Snodgrass, Ahmed Khalifa, Sebastian Risi, Georgios N. Yannakakis, Julian Togelius

This article surveys the various deep learning methods that have been applied to generate game content directly or indirectly, discusses deep learning methods that could be used for content generation purposes but are rarely used today, and envisages some limitations and potential future directions of deep learning for procedural content generation.

AI and Wargaming

no code implementations18 Sep 2020 James Goodman, Sebastian Risi, Simon Lucas

Recent progress in Game AI has demonstrated that given enough data from human gameplay, or experience gained via simulations, machines can rival or surpass the most skilled human players in classic games such as Go, or commercial computer games such as Starcraft.


Meta-Learning through Hebbian Plasticity in Random Networks

4 code implementations NeurIPS 2020 Elias Najarro, Sebastian Risi

We find that starting from completely random weights, the discovered Hebbian rules enable an agent to navigate a dynamical 2D-pixel environment; likewise they allow a simulated 3D quadrupedal robot to learn how to walk while adapting to morphological damage not seen during training and in the absence of any explicit reward or error signal in less than 100 timesteps.

Navigate reinforcement-learning +1

Capturing Local and Global Patterns in Procedural Content Generation via Machine Learning

no code implementations26 May 2020 Vanessa Volz, Niels Justesen, Sam Snodgrass, Sahar Asadi, Sami Purmonen, Christoffer Holmgård, Julian Togelius, Sebastian Risi

Recent procedural content generation via machine learning (PCGML) methods allow learning from existing content to produce similar content automatically.

BIG-bench Machine Learning

Finding Game Levels with the Right Difficulty in a Few Trials through Intelligent Trial-and-Error

1 code implementation15 May 2020 Miguel González-Duque, Rasmus Berg Palm, David Ha, Sebastian Risi

The approach can reliably find levels with a specific target difficulty for a variety of planning agents in only a few trials, while maintaining an understanding of their skill landscape.

Bayesian Optimization

Safe Reinforcement Learning through Meta-learned Instincts

no code implementations6 May 2020 Djordje Grbic, Sebastian Risi

Here we introduce a novel approach called Meta-Learned Instinctual Networks (MLIN) that allows agents to safely learn during their lifetime while avoiding potentially hazardous states.

Meta-Learning Navigate +3

CPPN2GAN: Combining Compositional Pattern Producing Networks and GANs for Large-scale Pattern Generation

2 code implementations3 Apr 2020 Jacob Schrum, Vanessa Volz, Sebastian Risi

In particular, GAN output does not scale to arbitrary dimensions, and there is no obvious way of combining multiple GAN outputs into a cohesive whole, which would be useful in many areas, such as the generation of video game levels.

Interactive Evolution and Exploration Within Latent Level-Design Space of Generative Adversarial Networks

1 code implementation31 Mar 2020 Jacob Schrum, Jake Gutierrez, Vanessa Volz, Jialin Liu, Simon Lucas, Sebastian Risi

A user study shows that both the evolution and latent space exploration features are appreciated, with a slight preference for direct exploration, but combining these features allows users to discover even better levels.

From Chess and Atari to StarCraft and Beyond: How Game AI is Driving the World of AI

no code implementations24 Feb 2020 Sebastian Risi, Mike Preuss

This paper reviews the field of Game AI, which not only deals with creating agents that can play a certain game, but also with areas as diverse as creating game content automatically, game analytics, or player modelling.


Deep Innovation Protection: Confronting the Credit Assignment Problem in Training Heterogeneous Neural Architectures

1 code implementation29 Dec 2019 Sebastian Risi, Kenneth O. Stanley

Deep reinforcement learning approaches have shown impressive results in a variety of different domains, however, more complex heterogeneous architectures such as world models require the different neural components to be trained separately instead of end-to-end.

Multiobjective Optimization

Increasing Generality in Machine Learning through Procedural Content Generation

no code implementations29 Nov 2019 Sebastian Risi, Julian Togelius

Procedural Content Generation (PCG) refers to the practice, in videogames and other games, of generating content such as levels, quests, or characters algorithmically.

BIG-bench Machine Learning

CG-GAN: An Interactive Evolutionary GAN-based Approach for Facial Composite Generation)

no code implementations28 Nov 2019 Nicola Zaltron, Luisa Zurlo, Sebastian Risi

CG-GAN offers a novel way of generating and handling static and animated photo-realistic facial composites, with the possibility of combining multiple representations of the same perpetrator, generated by different eyewitnesses.

Bootstrapping Conditional GANs for Video Game Level Generation

no code implementations3 Oct 2019 Ruben Rodriguez Torrado, Ahmed Khalifa, Michael Cerny Green, Niels Justesen, Sebastian Risi, Julian Togelius

Theresults demonstrate that the new approach does not only gen-erate a larger number of levels that are playable but also gen-erates fewer duplicate levels compared to a standard GAN.

Image Generation

Deep Innovation Protection

no code implementations25 Sep 2019 Sebastian Risi, Kenneth O. Stanley

Evolutionary-based optimization approaches have recently shown promising results in domains such as Atari and robot locomotion but less so in solving 3D tasks directly from pixels.

Multiobjective Optimization

An artifcial life approach to studying niche differentiation in soundscape ecology

no code implementations30 Jul 2019 David Kadish, Sebastian Risi, Laura Beloff

Artificial life simulations are an important tool in the study of ecological phenomena that can be difficult to examine directly in natural environments.

Artificial Life

Deep Neuroevolution of Recurrent and Discrete World Models

4 code implementations28 Apr 2019 Sebastian Risi, Kenneth O. Stanley

Instead of the relatively simple architectures employed in most RL experiments, world models rely on multiple different neural components that are responsible for visual information processing, memory, and decision-making.

Car Racing Decision Making +1

Illuminating Generalization in Deep Reinforcement Learning through Procedural Level Generation

1 code implementation28 Jun 2018 Niels Justesen, Ruben Rodriguez Torrado, Philip Bontrager, Ahmed Khalifa, Julian Togelius, Sebastian Risi

However, when neural networks are trained in a fixed environment, such as a single level in a video game, they will usually overfit and fail to generalize to new levels.

Clustering Dimensionality Reduction +2

Evolving Mario Levels in the Latent Space of a Deep Convolutional Generative Adversarial Network

3 code implementations2 May 2018 Vanessa Volz, Jacob Schrum, Jialin Liu, Simon M. Lucas, Adam Smith, Sebastian Risi

This paper trains a GAN to generate levels for Super Mario Bros using a level from the Video Game Level Corpus.

SNES Games

Automated Curriculum Learning by Rewarding Temporally Rare Events

1 code implementation19 Mar 2018 Niels Justesen, Sebastian Risi

We demonstrate that this \emph{Rarity of Events} (RoE) approach enables the agent to succeed in challenging VizDoom scenarios without access to the extrinsic reward from the environment.

Reinforcement Learning (RL)

Deep Interactive Evolution

1 code implementation24 Jan 2018 Philip Bontrager, Wending Lin, Julian Togelius, Sebastian Risi

The main insight in this paper is that a GAN trained on a specific target domain can act as a compact and robust genotype-to-phenotype mapping (i. e. most produced phenotypes do resemble valid domain artifacts).

Image Generation

HyperENTM: Evolving Scalable Neural Turing Machines through HyperNEAT

1 code implementation12 Oct 2017 Jakob Merrild, Mikkel Angaju Rasmussen, Sebastian Risi

We demonstrate that using the indirect HyperNEAT encoding allows for training on small memory vectors in a bit-vector copy task and then applying the knowledge gained from such training to speed up training on larger size memory vectors.

Deep Learning for Video Game Playing

no code implementations25 Aug 2017 Niels Justesen, Philip Bontrager, Julian Togelius, Sebastian Risi

In this article, we review recent Deep Learning advances in the context of how they have been applied to play different types of video games such as first-person shooters, arcade games, and real-time strategy games.

BIG-bench Machine Learning Real-Time Strategy Games

Learning Macromanagement in StarCraft from Replays using Deep Learning

no code implementations12 Jul 2017 Niels Justesen, Sebastian Risi

The real-time strategy game StarCraft has proven to be a challenging environment for artificial intelligence techniques, and as a result, current state-of-the-art solutions consist of numerous hand-crafted modules.


Born to Learn: the Inspiration, Progress, and Future of Evolved Plastic Artificial Neural Networks

no code implementations30 Mar 2017 Andrea Soltoggio, Kenneth O. Stanley, Sebastian Risi

Inspired by such intricate natural phenomena, Evolved Plastic Artificial Neural Networks (EPANNs) use simulated evolution in-silico to breed plastic neural networks with a large variety of dynamics, architectures, and plasticity rules: these artificial systems are composed of inputs, outputs, and plastic components that change in response to experiences in an environment.

Deep-Spying: Spying using Smartwatch and Deep Learning

1 code implementation17 Dec 2015 Tony Beltramelli, Sebastian Risi

Wearable technologies are today on the rise, becoming more common and broadly available to mainstream users.

Increasing Behavioral Complexity for Evolved Virtual Creatures with the ESP Method

no code implementations27 Oct 2015 Dan Lessin, Don Fussell, Risto Miikkulainen, Sebastian Risi

Since their introduction in 1994 (Sims), evolved virtual creatures (EVCs) have employed the coevolution of morphology and control to produce high-impact work in multiple fields, including graphics, evolutionary computation, robotics, and artificial life.

Artificial Life

The Case for a Mixed-Initiative Collaborative Neuroevolution Approach

no code implementations5 Aug 2014 Sebastian Risi, Jinhong Zhang, Rasmus Taarnby, Peter Greve, Jan Piskur, Antonios Liapis, Julian Togelius

It is clear that the current attempts at using algorithms to create artificial neural networks have had mixed success at best when it comes to creating large networks and/or complex behavior.

Common Sense Reasoning

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