Search Results for author:
Found 68 papers, 32 papers with code
Collective Innovation in Groups of Large Language Models
Here, we contribute a computational study of collective innovation where agents are Large Language Models (LLMs) that play Little Alchemy 2, a creative video game originally developed for humans that, as we argue, captures useful aspects of innovation landscapes not present in previous test-beds.
LayerShuffle: Enhancing Robustness in Vision Transformers by Randomizing Layer Execution Order
Finally, we layer-prune our models at test time and find that their performance declines gracefully.
Evolving Self-Assembling Neural Networks: From Spontaneous Activity to Experience-Dependent Learning
Biological neural networks are characterized by their high degree of plasticity, a core property that enables the remarkable adaptability of natural organisms.
From Text to Life: On the Reciprocal Relationship between Artificial Life and Large Language Models
Large Language Models (LLMs) have taken the field of AI by storm, but their adoption in the field of Artificial Life (ALife) has been, so far, relatively reserved.
Meta-Learning an Evolvable Developmental Encoding
This is in contrast to the representation that maps DNAs to phenotypes in biological organisms, which is at the hear of biological complexity and evolvability.
Growing Artificial Neural Networks for Control: the Role of Neuronal Diversity
Artificial neural networks (ANNs), on the other hand, are traditionally optimized in the space of weights.
Structurally Flexible Neural Networks: Evolving the Building Blocks for General Agents
Artificial neural networks used for reinforcement learning are structurally rigid, meaning that each optimized parameter of the network is tied to its specific placement in the network structure.
Algorithmic Ways of Seeing: Using Object Detection to Facilitate Art Exploration
Second, we present the design and development of an app that enables exploration of an art museum's collection.
Towards Self-Assembling Artificial Neural Networks through Neural Developmental Programs
Biological nervous systems are created in a fundamentally different way than current artificial neural networks.
Fooling Contrastive Language-Image Pre-trained Models with CLIPMasterPrints
We investigate the properties of the mined images, and find that images trained on a small number of image captions generalize to a much larger number of semantically related captions.
Learning to Act through Evolution of Neural Diversity in Random Neural Networks
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
MarioGPT can not only generate diverse levels, but can be text-prompted for controllable level generation, addressing one of the key challenges of current PCG techniques.
Skill Decision Transformer
However many of these methods only optimize for high returns, and may not extract much information from a diverse dataset of trajectories.
Severe Damage Recovery in Evolving Soft Robots through Differentiable Programming
Biological systems are very robust to morphological damage, but artificial systems (robots) are currently not.
Mario Plays on a Manifold: Generating Functional Content in Latent Space through Differential Geometry
Deep generative models can automatically create content of diverse types.
Minimal Neural Network Models for Permutation Invariant Agents
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
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
In contrast to deep reinforcement learning agents, biological neural networks are grown through a self-organized developmental process.
A Unified Substrate for Body-Brain Co-evolution
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
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
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
Random exploration is one of the main mechanisms through which reinforcement learning (RL) finds well-performing policies.
Dealing with Adversarial Player Strategies in the Neural Network Game iNNk through Ensemble Learning
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.
Hybrid Encoding For Generating Large Scale Game Level Patterns With Local Variations
However, collections of latent vectors can also be evolved directly, producing more chaotic levels.
Fast Game Content Adaptation Through Bayesian-based Player Modelling
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
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
For a BM, making predictions with the lowest expected loss requires integrating over the posterior distribution.
Growing 3D Artefacts and Functional Machines with Neural Cellular Automata
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
We generate a large dataset for training and validation by modifying the images in the COCO dataset using AdaIn style transfer.
Ranked #5 on
Object Detection
on PeopleArt
Regenerating Soft Robots through Neural Cellular Automata
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
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
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.
Evolutionary Planning in Latent Space
Planning is a powerful approach to reinforcement learning with several desirable properties.
Testing the Genomic Bottleneck Hypothesis in Hebbian Meta-Learning
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.
The power of pictures: using ML assisted image generation to engage the crowd in complex socioscientific problems
Human-computer image generation using Generative Adversarial Networks (GANs) is becoming a well-established methodology for casual entertainment and open artistic exploration.
Deep Learning for Procedural Content Generation
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
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.
iNNk: A Multi-Player Game to Deceive a Neural Network
This paper presents iNNK, a multiplayer drawing game where human players team up against an NN.
Meta-Learning through Hebbian Plasticity in Random Networks
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.
Capturing Local and Global Patterns in Procedural Content Generation via Machine Learning
Recent procedural content generation via machine learning (PCGML) methods allow learning from existing content to produce similar content automatically.
Finding Game Levels with the Right Difficulty in a Few Trials through Intelligent Trial-and-Error
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.
Safe Reinforcement Learning through Meta-learned Instincts
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.
CPPN2GAN: Combining Compositional Pattern Producing Networks and GANs for Large-scale Pattern Generation
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
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
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.
Revealing Neural Network Bias to Non-Experts Through Interactive Counterfactual Examples
AI algorithms are not immune to biases.
Deep Innovation Protection: Confronting the Credit Assignment Problem in Training Heterogeneous Neural Architectures
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.
Increasing Generality in Machine Learning through Procedural Content Generation
Procedural Content Generation (PCG) refers to the practice, in videogames and other games, of generating content such as levels, quests, or characters algorithmically.
CG-GAN: An Interactive Evolutionary GAN-based Approach for Facial Composite Generation)
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
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.
Deep Innovation Protection
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.
An artifcial life approach to studying niche differentiation in soundscape ecology
Artificial life simulations are an important tool in the study of ecological phenomena that can be difficult to examine directly in natural environments.
Learning a Behavioral Repertoire from Demonstrations
Imitation Learning (IL) is a machine learning approach to learn a policy from a dataset of demonstrations.
Deep Neuroevolution of Recurrent and Discrete World Models
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.
Illuminating Generalization in Deep Reinforcement Learning through Procedural Level Generation
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.
Evolving Mario Levels in the Latent Space of a Deep Convolutional Generative Adversarial Network
This paper trains a GAN to generate levels for Super Mario Bros using a level from the Video Game Level Corpus.
A Robot to Shape your Natural Plant: The Machine Learning Approach to Model and Control Bio-Hybrid Systems
The evolved controllers augment the plants' natural light-finding and tissue-stiffening behaviors to avoid obstacles and grow desired shapes.
Automated Curriculum Learning by Rewarding Temporally Rare Events
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.
Deep Interactive Evolution
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).
HyperENTM: Evolving Scalable Neural Turing Machines through HyperNEAT
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
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.
Learning Macromanagement in StarCraft from Replays using Deep Learning
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
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.
Using Indirect Encoding of Multiple Brains to Produce Multimodal Behavior
Indirect encodings can potentially answer this challenge.
Deep-Spying: Spying using Smartwatch and Deep Learning
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
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.
Neuroevolution in Games: State of the Art and Open Challenges
This paper surveys research on applying neuroevolution (NE) to games.
The Case for a Mixed-Initiative Collaborative Neuroevolution Approach
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.
