Author name cluster

Sebastian Risi

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

12 papers

2 author rows

IROS Conference 2025 Conference Paper

Bio-Inspired Plastic Neural Networks for Zero-Shot Out-of-Distribution Generalization in Complex Animal-Inspired Robots

Binggwong Leung
Worasuchad Haomachai
Joachim Winther Pedersen
Sebastian Risi
Poramate Manoonpong

Artificial neural networks can be used to solve a variety of robotic tasks. However, they risk failing catastrophically when faced with out-of-distribution (OOD) situations. Several approaches have employed a type of synaptic plasticity known as Hebbian learning that can dynamically adjust weights based on local neural activities. Research has shown that synaptic plasticity can make policies more robust and help them adapt to unforeseen changes in the environment. However, networks augmented with Hebbian learning can lead to weight divergence, resulting in network instability. Furthermore, such Hebbian networks have not yet been applied to solve legged locomotion in complex real robots with many degrees of freedom. In this work, we improve the Hebbian network with a weight normalization mechanism for preventing weight divergence, analyze the principal components of the Hebbian’s weights, and perform a thorough evaluation of network performance in locomotion control for real 18-DOF dung beetle-like and 16-DOF gecko-like robots. We find that the Hebbian-based plastic network can execute zero-shot sim-to-real adaptation locomotion and generalize to unseen conditions, such as uneven terrain and morphological damage.

Details

NeurIPS Conference 2025 Conference Paper

Continuous Thought Machines

Luke Darlow
Ciaran Regan
Sebastian Risi
Jeffrey Seely
Llion Jones

Biological brains demonstrate complex neural activity, where neural dynamics are critical to how brains process information. Most artificial neural networks ignore the complexity of individual neurons. We challenge that paradigm. By incorporating neuron-level processing and synchronization, we reintroduce neural timing as a foundational element. We present the Continuous Thought Machine (CTM), a model designed to leverage neural dynamics as its core representation. The CTM has two innovations: (1) neuron-level temporal processing}, where each neuron uses unique weight parameters to process incoming histories; and (2) neural synchronization as a latent representation. The CTM aims to strike a balance between neuron abstractions and biological realism. It operates at a level of abstraction that effectively captures essential temporal dynamics while remaining computationally tractable. We demonstrate the CTM's performance and versatility across a range of tasks, including solving 2D mazes, ImageNet-1K classification, parity computation, and more. Beyond displaying rich internal representations and offering a natural avenue for interpretation owing to its internal process, the CTM is able to perform tasks that require complex sequential reasoning. The CTM can also leverage adaptive compute, where it can stop earlier for simpler tasks, or keep computing when faced with more challenging instances. The goal of this work is to share the CTM and its associated innovations, rather than pushing for new state-of-the-art results. To that end, we believe the CTM represents a significant step toward developing more biologically plausible and powerful artificial intelligence systems. We provide an accompanying interactive online demonstration and an extended technical report.

PDF Details

TMLR Journal 2024 Journal Article

Fooling Contrastive Language-Image Pre-Trained Models with CLIPMasterPrints

Matthias Freiberger
Peter Kun
Christian Igel
Anders Sundnes Løvlie
Sebastian Risi

Models leveraging both visual and textual data such as Contrastive Language-Image Pre-training (CLIP), are the backbone of many recent advances in artificial intelligence. In this work, we show that despite their versatility, such models are vulnerable to what we refer to as fooling master images. Fooling master images are capable of maximizing the confidence score of a CLIP model for a significant number of widely varying prompts, while being either unrecognizable or unrelated to the attacked prompts for humans. We demonstrate how fooling master images can be mined using stochastic gradient descent, projected gradient descent, or gradient-free optimisation. Contrary to many common adversarial attacks, the gradient-free optimisation approach allows us to mine fooling examples even when the weights of the model are not accessible. 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. Finally, we evaluate possible mitigation strategies and find that vulnerability to fooling master examples appears to be closely related to a modality gap in contrastive pre-trained multi-modal networks.

PDF Details

NeurIPS Conference 2023 Conference Paper

MarioGPT: Open-Ended Text2Level Generation through Large Language Models

Shyam Sudhakaran
Miguel González-Duque
Matthias Freiberger
Claire Glanois
Elias Najarro
Sebastian Risi

Procedural Content Generation (PCG) is a technique to generate complex and diverse environments in an automated way. However, while generating content with PCG methods is often straightforward, generating meaningful content that reflects specific intentions and constraints remains challenging. Furthermore, many PCG algorithms lack the ability to generate content in an open-ended manner. Recently, Large Language Models (LLMs) have shown to be incredibly effective in many diverse domains. These trained LLMs can be fine-tuned, re-using information and accelerating training for new tasks. Here, we introduce MarioGPT, a fine-tuned GPT2 model trained to generate tile-based game levels, in our case Super Mario Bros levels. 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. As far as we know, MarioGPT is the first text-to-level model and combined with novelty search it enables the generation of diverse levels with varying play-style dynamics (i. e. player paths) and the open-ended discovery of an increasingly diverse range of content. Code available at https: //github. com/shyamsn97/mario-gpt.

PDF Details

IROS Conference 2022 Conference Paper

Physical Neural Cellular Automata for 2D Shape Classification

Kathryn Walker
Rasmus Berg Palm
Rodrigo Moreno
Andrés Faiña
Kasper Støy
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. Biological systems possess the ability not only to self-reconfigure but also to self-classify themselves to determine a general shape and function. Previous work into modular robotics systems has only enabled self-recognition and self-reconfiguration into a specific target shape, missing the inherent robustness present in nature to self-classify. In this paper we therefore take advantage of recent advances in deep learning and neural cellular automata, and present a simple modular 2D robotic system that can infer its own class of shape through the local communication of its components. Furthermore, we show that our system can be successfully transferred to hardware which thus opens op-portunities for future self-classifying machines. Code available at https://github.com/kattwalker/projectcube.Video available at https://youtu.be/0TCOkE4keyc.

Details

ICLR Conference 2022 Conference Paper

Variational Neural Cellular Automata

Rasmus Berg Palm
Miguel González Duque
Shyam Sudhakaran
Sebastian Risi

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 of this biological generative process, we propose a generative model, the Variational Neural Cellular Automata (VNCA), which is loosely inspired by the biological processes of cellular growth and differentiation. Unlike previous related works, the VNCA is a proper probabilistic generative model, and we evaluate it according to best practices. We find that the VNCA learns to reconstruct samples well and that despite its relatively few parameters and simple local-only communication, the VNCA can learn to generate a large variety of output from information encoded in a common vector format. While there is a significant gap to the current state-of-the-art in terms of generative modeling performance, we show that the VNCA can learn a purely self-organizing generative process of data. Additionally, the self-organizing nature bestows the VNCA with some inherent robustness against perturbations in the early stages of growth.

Details

AAAI Conference 2021 Conference Paper

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

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. While a simple genetic algorithm recently showed end-to-end training is possible, it failed to solve a more complex 3D task. This paper presents a method called Deep Innovation Protection (DIP) that addresses the credit assignment problem in training complex heterogenous neural network models end-to-end for such environments. The main idea behind the approach is to employ multiobjective optimization to temporally reduce the selection pressure on specific components in multi-component network, allowing other components to adapt. We investigate the emergent representations of these evolved networks, which learn to predict properties important for the survival of the agent, without the need for a specific forward-prediction loss.

PDF Details

AAAI Conference 2020 Conference Paper

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

Nicola Zaltron
Luisa Zurlo
Sebastian Risi

Facial composites are graphical representations of an eyewitness’s memory of a face. Many digital systems are available for the creation of such composites but are either unable to reproduce features unless previously designed or do not allow holistic changes to the image. In this paper, we improve the efﬁciency of composite creation by removing the reliance on expert knowledge and letting the system learn to represent faces from examples. The novel approach, Composite Generating GAN (CG-GAN), applies generative and evolutionary computation to allow casual users to easily create facial composites. Speciﬁcally, CG-GAN utilizes the generator network of a pg-GAN to create high-resolution human faces. Users are provided with several functions to interactively breed and edit faces. 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. Figure 1: Example composite built using CG-GAN.

PDF Details

NeurIPS Conference 2020 Conference Paper

Meta-Learning through Hebbian Plasticity in Random Networks

Elias Najarro
Sebastian Risi

Lifelong learning and adaptability are two defining aspects of biological agents. Modern reinforcement learning (RL) approaches have shown significant progress in solving complex tasks, however once training is concluded, the found solutions are typically static and incapable of adapting to new information or perturbations. While it is still not completely understood how biological brains learn and adapt so efficiently from experience, it is believed that synaptic plasticity plays a prominent role in this process. Inspired by this biological mechanism, we propose a search method that, instead of optimizing the weight parameters of neural networks directly, only searches for synapse-specific Hebbian learning rules that allow the network to continuously self-organize its weights during the lifetime of the agent. We demonstrate our approach on several reinforcement learning tasks with different sensory modalities and more than 450K trainable plasticity parameters. 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.

PDF Details

IS Journal 2014 Journal Article

An Anarchy of Methods: Current Trends in How Intelligence Is Abstracted in AI

Joel Lehman
Jeff Clune
Sebastian Risi

Artificial intelligence (AI) is a sprawling field encompassing a diversity of approaches to machine intelligence and disparate perspectives on how intelligence should be viewed. Because researchers often engage only within their own specialized area of AI, there are many interesting broad questions about AI as a whole that often go unanswered. How should intelligence be abstracted in AI research? Which subfields, techniques, and abstractions are most promising? Why do researchers bet their careers on the particular abstractions and techniques of their chosen subfield of AI? Should AI research be "bio-inspired" and remain faithful to the process that produced intelligence (evolution) or the biological substrate that enables it (networks of neurons)? Discussing these big-picture questions motivated us to organize an AAAI Fall Symposium, which gathered participants across AI subfields to present and debate their views. This article distills the resulting insights.

Details DOI

IROS Conference 2011 Conference Paper

Task switching in multirobot learning through indirect encoding

David B. D'Ambrosio
Joel Lehman
Sebastian Risi
Kenneth O. Stanley

Multirobot domains are a challenge for learning algorithms because they require robots to learn to cooperate to achieve a common goal. The challenge only becomes greater when robots must perform heterogeneous tasks to reach that goal. Multiagent HyperNEAT is a neuroevolutionary method (i. e. a method that evolves neural networks) that has proven successful in several cooperative multiagent domains by exploiting the concept of policy geometry, which means the policies of team members are learned as a function of how they relate to each other based on canonical starting positions. This paper extends the multiagent HyperNEAT algorithm by introducing situational policy geometry, which allows each agent to encode multiple policies that can be switched depending on the agent's state. This concept is demonstrated both in simulation and in real Khepera III robots in a patrol and return task, where robots must cooperate to cover an area and return home when called. Robot teams that are trained with situational policy geometry are compared to teams that are not and shown to find solutions more consistently that are also able to transfer to the real world.

Details

AAMAS Conference 2010 Conference Paper

Evolving Policy Geometry for Scalable Multiagent Learning

David D'Ambrosio
Joel Lehman
Sebastian Risi
Kenneth Stanley

A major challenge for traditional approaches to multiagentlearning is to train teams that easily scale to include additional agents. The problem is that such approaches typically encode each agent's policy separately. Such separationmeans that computational complexity explodes as the number of agents in the team increases, and also leads to theproblem of reinvention: Skills that should be shared amongagents must be rediscovered separately for each agent. Toaddress this problem, this paper presents an alternative evolutionary approach to multiagent learning called multiagentHyperNEAT that encodes the team as a pattern of relatedpolicies rather than as a set of individual agents. To capturethis pattern, a policy geometry is introduced to describe therelationship between each agent's policy and its canonicalgeometric position within the team. Because policy geometry can encode variations of a shared skill across all of thepolicies it represents, the problem of reinvention is avoided. Furthermore, because the policy geometry of a particularteam can be sampled at any resolution, it acts as a heuristicfor generating policies for teams of any size, producing apowerful new capability for multiagent learning. In this paper, multiagent HyperNEAT is tested in predator-prey androom-clearing domains. In both domains the results are effective teams that can be successfully scaled to larger teamsizes without any further training.

PDF