# Meta-Learning through Hebbian Plasticity in Random Networks

arXiv: https://arxiv.org/abs/2007.02686 · HTML: https://mlsanity.com/paper/2007.02686/

## Key facts

- Cited by 47 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 6 Jul 2020.

## Built on by (most cited first, 30 of 47)

- [Hypernetworks in Meta-Reinforcement Learning](https://mlsanity.com/paper/2210.11348/) (2022)
- [A Modern Self-Referential Weight Matrix That Learns to Modify Itself](https://mlsanity.com/paper/2202.05780/) (2022)
- [Brain-inspired learning in artificial neural networks: a review](https://mlsanity.com/paper/2305.11252/) (2023)
- [Introducing Symmetries to Black Box Meta Reinforcement Learning](https://mlsanity.com/paper/2109.10781/) (2021)
- [HyperNCA: Growing Developmental Networks with Neural Cellular Automata](https://mlsanity.com/paper/2204.11674/) (2022)
- [Convergence and Alignment of Gradient Descent with Random Backpropagation Weights](https://mlsanity.com/paper/2106.06044/) (2021)
- [Backprop-Free Reinforcement Learning with Active Neural Generative Coding](https://mlsanity.com/paper/2107.07046/) (2021)
- [Meta-Learning Bidirectional Update Rules](https://mlsanity.com/paper/2104.04657/) (2021)
- [Goal-Conditioned Generators of Deep Policies](https://mlsanity.com/paper/2207.01570/) (2022)
- [Spiking Neural Networks and Bio-Inspired Supervised Deep Learning: A Survey](https://mlsanity.com/paper/2307.16235/) (2023)
- [Fast weight programming and linear transformers: from machine learning to neurobiology](https://mlsanity.com/paper/2508.08435/) (2025)
- [Fast On-Device Adaptation for Spiking Neural Networks via Online-Within-Online Meta-Learning](https://mlsanity.com/paper/2103.03901/) (2021)
- [Active Predicting Coding: Brain-Inspired Reinforcement Learning for Sparse Reward Robotic Control Problems](https://mlsanity.com/paper/2209.09174/) (2022)
- [Benchmarking General-Purpose In-Context Learning](https://mlsanity.com/paper/2405.17234/) (2024)
- [Evolving Decomposed Plasticity Rules for Information-Bottlenecked Meta-Learning](https://mlsanity.com/paper/2109.03554/) (2021)
- [Pretraining Recurrent Networks without Recurrence](https://mlsanity.com/paper/2606.06479/) (2026)
- [Meta-Reinforcement Learning with Self-Modifying Networks](https://mlsanity.com/paper/2202.02363/) (2022)
- [Severe Damage Recovery in Evolving Soft Robots through Differentiable Programming](https://mlsanity.com/paper/2206.06674/) (2022)
- [Hebbian and Gradient-based Plasticity Enables Robust Memory and Rapid Learning in RNNs](https://mlsanity.com/paper/2302.03235/) (2023)
- [Discovering Adaptable Symbolic Algorithms from Scratch](https://mlsanity.com/paper/2307.16890/) (2023)
- [Structurally Flexible Neural Networks: Evolving the Building Blocks for General Agents](https://mlsanity.com/paper/2404.15193/) (2024)
- [Evolving Self-Assembling Neural Networks: From Spontaneous Activity to Experience-Dependent Learning](https://mlsanity.com/paper/2406.09787/) (2024)
- [Towards Large-Scale In-Context Reinforcement Learning by Meta-Training in Randomized Worlds](https://mlsanity.com/paper/2502.02869/) (2025)
- [Beyond accuracy: generalization properties of bio-plausible temporal credit assignment rules](https://mlsanity.com/paper/2206.00823/) (2022)
- [Three-Factor Learning in Spiking Neural Networks: An Overview of Methods and Trends from a Machine Learning Perspective](https://mlsanity.com/paper/2504.05341/) (2025)
- [Where to Bind Matters: Hebbian Fast Weights in Vision Transformers for Few-Shot Character Recognition](https://mlsanity.com/paper/2605.02920/) (2026)
- [Biological connectomes as a representation for the architecture of artificial neural networks](https://mlsanity.com/paper/2209.14406/) (2022)
- [Unsupervised 3D Object Learning through Neuron Activity aware Plasticity](https://mlsanity.com/paper/2302.11622/) (2023)
- [Learning to Act through Evolution of Neural Diversity in Random Neural Networks](https://mlsanity.com/paper/2305.15945/) (2023)
- [Same World, Differently Given: History-Dependent Perceptual Reorganization in Artificial Agents](https://mlsanity.com/paper/2604.04637/) (2026)

## Abstract (arXiv)

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. Code is available at https://github.com/enajx/HebbianMetaLearning.