# Meta-learning three-factor plasticity rules for structured credit assignment with sparse feedback

arXiv: https://arxiv.org/abs/2512.09366 · HTML: https://mlsanity.com/paper/2512.09366/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 6 of its 34 references that are in the map.
- First posted on arXiv 10 Dec 2025.

## Builds on (most cited first, 6 of 6)

- [Differentiable plasticity: training plastic neural networks with backpropagation](https://mlsanity.com/paper/1804.02464/) (2018)
- [Towards deep learning with segregated dendrites](https://mlsanity.com/paper/1610.00161/) (2016)
- [Eligibility Traces and Plasticity on Behavioral Time Scales: Experimental Support of neoHebbian Three-Factor Learning Rules](https://mlsanity.com/paper/1801.05219/) (2018)
- [Meta-Learning Biologically Plausible Plasticity Rules with Random Feedback Pathways](https://mlsanity.com/paper/2210.16414/) (2022)
- [Learning to Learn with Feedback and Local Plasticity](https://mlsanity.com/paper/2006.09549/) (2020)
- [Nonlinear Hebbian learning as a unifying principle in receptive field formation](https://mlsanity.com/paper/1601.00701/) (2016)

## Abstract (arXiv)

Biological neural networks learn complex behaviors from sparse, delayed feedback using local synaptic plasticity, yet the mechanisms enabling structured credit assignment remain elusive. In contrast, artificial recurrent networks solving similar tasks typically rely on biologically implausible global learning rules or hand-crafted local updates. The space of local plasticity rules capable of supporting learning from delayed reinforcement remains largely unexplored. Here, we present a meta-learning framework that discovers local learning rules for structured credit assignment in recurrent networks trained with sparse feedback. Our approach interleaves local neo-Hebbian-like updates during task execution with an outer loop that optimizes plasticity parameters via tangent-propagation through learning. The resulting three-factor learning rules enable long-timescale credit assignment using only local information and delayed rewards, offering new insights into biologically grounded mechanisms for learning in recurrent circuits.