# Learning to solve the credit assignment problem

arXiv: https://arxiv.org/abs/1906.00889 · HTML: https://mlsanity.com/paper/1906.00889/

## Key facts

- Cited by 27 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 3 Jun 2019.

## Built on by (most cited first, 27 of 27)

- [On Training Implicit Models](https://mlsanity.com/paper/2111.05177/) (2021)
- [Credit Assignment in Neural Networks through Deep Feedback Control](https://mlsanity.com/paper/2106.07887/) (2021)
- [SCAR: Shapley Credit Assignment for More Efficient RLHF](https://mlsanity.com/paper/2505.20417/) (2025)
- [Brain-Inspired Machine Intelligence: A Survey of Neurobiologically-Plausible Credit Assignment](https://mlsanity.com/paper/2312.09257/) (2023)
- [Meta-Learning Biologically Plausible Plasticity Rules with Random Feedback Pathways](https://mlsanity.com/paper/2210.16414/) (2022)
- [Minimizing Control for Credit Assignment with Strong Feedback](https://mlsanity.com/paper/2204.07249/) (2022)
- [Learning efficient backprojections across cortical hierarchies in real time](https://mlsanity.com/paper/2212.10249/) (2022)
- [Gradient-Free Training of Recurrent Neural Networks using Random Perturbations](https://mlsanity.com/paper/2405.08967/) (2024)
- [Training Deep Architectures Without End-to-End Backpropagation: A Survey on the Provably Optimal Methods](https://mlsanity.com/paper/2101.03419/) (2021)
- [Distinguishing Learning Rules with Brain Machine Interfaces](https://mlsanity.com/paper/2206.13448/) (2022)
- [Prompt Baking](https://mlsanity.com/paper/2409.13697/) (2024)
- [Target Propagation via Regularized Inversion](https://mlsanity.com/paper/2112.01453/) (2021)
- [Residual Q-Networks for Value Function Factorizing in Multi-Agent Reinforcement Learning](https://mlsanity.com/paper/2205.15245/) (2022)
- [Multi-compartment Neuron and Population Encoding Powered Spiking Neural Network for Deep Distributional Reinforcement Learning](https://mlsanity.com/paper/2301.07275/) (2023)
- [InferNet for Delayed Reinforcement Tasks: Addressing the Temporal Credit Assignment Problem](https://mlsanity.com/paper/2105.00568/) (2021)
- [A Robust Backpropagation-Free Framework for Images](https://mlsanity.com/paper/2206.01820/) (2022)
- [Modeling Human Behavior Part II -- Cognitive approaches and Uncertainty](https://mlsanity.com/paper/2205.06483/) (2022)
- [Modeling Human Behavior Part I -- Learning and Belief Approaches](https://mlsanity.com/paper/2205.06485/) (2022)
- [Learning Using a Single Forward Pass](https://mlsanity.com/paper/2402.09769/) (2024)
- [Spike-based alignment learning solves the weight transport problem](https://mlsanity.com/paper/2503.02642/) (2025)
- [Front Contribution instead of Back Propagation](https://mlsanity.com/paper/2106.05569/) (2021)
- [Contribute to balance, wire in accordance: Emergence of backpropagation from a simple, bio-plausible neuroplasticity rule](https://mlsanity.com/paper/2405.14139/) (2024)
- [An experimental comparative study of backpropagation and alternatives for training binary neural networks for image classification](https://mlsanity.com/paper/2408.04460/) (2024)
- [Sign-Symmetry Learning Rules are Robust Fine-Tuners](https://mlsanity.com/paper/2502.05925/) (2025)
- [Information-Theoretic Greedy Layer-wise Training for Traffic Sign Recognition](https://mlsanity.com/paper/2510.27651/) (2025)
- [Forward Only Learning for Orthogonal Neural Networks of any Depth](https://mlsanity.com/paper/2512.20668/) (2025)
- [LC-ERD: Mining Latent Logic for Self-Evolving Reasoning via Consistency-Regulated Reward Decomposition](https://mlsanity.com/paper/2605.24005/) (2026)

## Abstract (arXiv)

Backpropagation is driving today's artificial neural networks (ANNs). However, despite extensive research, it remains unclear if the brain implements this algorithm. Among neuroscientists, reinforcement learning (RL) algorithms are often seen as a realistic alternative: neurons can randomly introduce change, and use unspecific feedback signals to observe their effect on the cost and thus approximate their gradient. However, the convergence rate of such learning scales poorly with the number of involved neurons. Here we propose a hybrid learning approach. Each neuron uses an RL-type strategy to learn how to approximate the gradients that backpropagation would provide. We provide proof that our approach converges to the true gradient for certain classes of networks. In both feedforward and convolutional networks, we empirically show that our approach learns to approximate the gradient, and can match or the performance of exact gradient-based learning. Learning feedback weights provides a biologically plausible mechanism of achieving good performance, without the need for precise, pre-specified learning rules.