Meta-learning through hebbian plasticity in random networks

E Najarro, S Risi - Advances in Neural Information …, 2020‏ - proceedings.neurips.cc
Lifelong learning and adaptability are two defining aspects of biological agents. Modern
reinforcement learning (RL) approaches have shown significant progress in solving complex …

Neuroevolution insights into biological neural computation

R Miikkulainen - Science, 2025‏ - science.org
This article reviews existing work and future opportunities in neuroevolution, an area of
machine learning in which evolutionary optimization methods such as genetic algorithms …

Evolving and merging hebbian learning rules: increasing generalization by decreasing the number of rules

JW Pedersen, S Risi - Proceedings of the Genetic and Evolutionary …, 2021‏ - dl.acm.org
Generalization to out-of-distribution (OOD) circumstances after training remains a challenge
for artificial agents. To improve the robustness displayed by plastic Hebbian neural …

Context meta-reinforcement learning via neuromodulation

E Ben-Iwhiwhu, J Dick, NA Ketz, PK Pilly, A Soltoggio - Neural Networks, 2022‏ - Elsevier
Meta-reinforcement learning (meta-RL) algorithms enable agents to adapt quickly to tasks
from few samples in dynamic environments. Such a feat is achieved through dynamic …

Meta reinforcement learning with hebbian learning

D Wang - 2022 IEEE 13th Annual Ubiquitous Computing …, 2022‏ - ieeexplore.ieee.org
Deep reinforcement learning achieves super-human performances at the cost of millions of
non-optimal interactions with environments. Ideally, a well trained deep reinforcement …

The configurable tree graph (ct-graph): measurable problems in partially observable and distal reward environments for lifelong reinforcement learning

A Soltoggio, E Ben-Iwhiwhu, C Peridis… - ar** reliable mechanisms for continuous local learning is a central challenge faced
by biological and artificial systems. Yet, how the environmental factors and structural …

Deep Reinforcement Learning for Combinatorial Optimization

D Wang - 2022‏ - search.proquest.com
Deep reinforcement learning proves its success in solving complicated combinatorial
problems. This work studies essential issues of DRL and its applications in the disassembly …

Neuromodulated networks for lifelong learning and adaptation

E Ben-Iwhiwhu - 2023‏ - repository.lboro.ac.uk
The development of robust and adaptable intelligent system has been a long standing grand
challenge. Recently, machine learning methods via neural networks have gained …