Search Results for author: Joachim Winther Pedersen

Found 8 papers, 2 papers with code

When Does Neuroevolution Outcompete Reinforcement Learning in Transfer Learning Tasks?

1 code implementation28 May 2025 Eleni Nisioti, Joachim Winther Pedersen, Erwan Plantec, Milton L. Montero, Sebastian Risi

The ability to continuously and efficiently transfer skills across tasks is a hallmark of biological intelligence and a long-standing goal in artificial systems.

reinforcement-learning Reinforcement Learning +2

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

no code implementations16 Mar 2025 Binggwong Leung, Worasuchad Haomachai, Joachim Winther Pedersen, Sebastian Risi, Poramate Manoonpong

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.

Out-of-Distribution Generalization

Growing Artificial Neural Networks for Control: the Role of Neuronal Diversity

1 code implementation14 May 2024 Eleni Nisioti, Erwan Plantec, Milton Montero, Joachim Winther Pedersen, Sebastian Risi

Artificial neural networks (ANNs), on the other hand, are traditionally optimized in the space of weights.

Diversity

Structurally Flexible Neural Networks: Evolving the Building Blocks for General Agents

no code implementations6 Apr 2024 Joachim Winther Pedersen, Erwan Plantec, Eleni Nisioti, Milton Montero, Sebastian Risi

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.

reinforcement-learning Reinforcement Learning

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.

Diversity

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.

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.

Clustering

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