# Dopamine-driven synaptic credit assignment in neural networks

arXiv: https://arxiv.org/abs/2510.22178 · HTML: https://mlsanity.com/paper/2510.22178/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 29 of its 97 references that are in the map.
- First posted on arXiv 25 Oct 2025.

## Builds on (most cited first, 29 of 29)

- [Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling](https://mlsanity.com/paper/1412.3555/) (2014)
- [Visualizing the Loss Landscape of Neural Nets](https://mlsanity.com/paper/1712.09913/) (2017)
- [Deep Learning in Neural Networks: An Overview](https://mlsanity.com/paper/1404.7828/) (2014)
- [Generating Sentences from a Continuous Space](https://mlsanity.com/paper/1511.06349/) (2015)
- [Evolution Strategies as a Scalable Alternative to Reinforcement Learning](https://mlsanity.com/paper/1703.03864/) (2017)
- [Direct Feedback Alignment Provides Learning in Deep Neural Networks](https://mlsanity.com/paper/1609.01596/) (2016)
- [Fast Convergence of Regularized Learning in Games](https://mlsanity.com/paper/1507.00407/) (2015)
- [Difference Target Propagation](https://mlsanity.com/paper/1412.7525/) (2014)
- [Sparse identification of nonlinear dynamics for model predictive control in the low-data limit](https://mlsanity.com/paper/1711.05501/) (2017)
- [Decoupled Neural Interfaces using Synthetic Gradients](https://mlsanity.com/paper/1608.05343/) (2016)
- [Assessing the Scalability of Biologically-Motivated Deep Learning Algorithms and Architectures](https://mlsanity.com/paper/1807.04587/) (2018)
- [Dendritic cortical microcircuits approximate the backpropagation algorithm](https://mlsanity.com/paper/1810.11393/) (2018)
- [How Auto-Encoders Could Provide Credit Assignment in Deep Networks via Target Propagation](https://mlsanity.com/paper/1407.7906/) (2014)
- [Eligibility Traces and Plasticity on Behavioral Time Scales: Experimental Support of neoHebbian Three-Factor Learning Rules](https://mlsanity.com/paper/1801.05219/) (2018)
- [Towards Biologically Plausible Deep Learning](https://mlsanity.com/paper/1502.04156/) (2015)
- [Error-driven Input Modulation: Solving the Credit Assignment Problem without a Backward Pass](https://mlsanity.com/paper/2201.11665/) (2022)
- [How Important is Weight Symmetry in Backpropagation?](https://mlsanity.com/paper/1510.05067/) (2015)
- [Random feedback weights support learning in deep neural networks](https://mlsanity.com/paper/1411.0247/) (2014)
- [Understanding Synthetic Gradients and Decoupled Neural Interfaces](https://mlsanity.com/paper/1703.00522/) (2017)
- [Direct Feedback Alignment with Sparse Connections for Local Learning](https://mlsanity.com/paper/1903.02083/) (2019)
- [Regret Minimization for Partially Observable Deep Reinforcement Learning](https://mlsanity.com/paper/1710.11424/) (2017)
- [Biological credit assignment through dynamic inversion of feedforward networks](https://mlsanity.com/paper/2007.05112/) (2020)
- [Working Memory Connections for LSTM](https://mlsanity.com/paper/2109.00020/) (2021)
- [Follow-the-Perturbed-Leader with Fr'echet-type Tail Distributions: Optimality in Adversarial Bandits and Best-of-Both-Worlds](https://mlsanity.com/paper/2403.05134/) (2024)
- [The Roles of Supervised Machine Learning in Systems Neuroscience](https://mlsanity.com/paper/1805.08239/) (2018)
- [Fixed-Weight Difference Target Propagation](https://mlsanity.com/paper/2212.10352/) (2022)
- [Target Propagation via Regularized Inversion](https://mlsanity.com/paper/2112.01453/) (2021)
- [Efficient Real Time Recurrent Learning through combined activity and parameter sparsity](https://mlsanity.com/paper/2303.05641/) (2023)
- [Brain Model State Space Reconstruction Using an LSTM Neural Network](https://mlsanity.com/paper/2301.08391/) (2023)

## Abstract (arXiv)

Solving the synaptic Credit Assignment Problem(CAP) is central to learning in both biological and artificial neural systems. Finding an optimal solution for synaptic CAP means setting the synaptic weights that assign credit to each neuron for influencing the final output and behavior of neural networks or animals. Gradient-based methods solve this problem in artificial neural networks using back-propagation, however, not in the most efficient way. For instance, back-propagation requires a chain of top-down gradient computations. This leads to an expensive optimization process in terms of computing power and memory linked with well-known weight transport and update locking problems. To address these shortcomings, we take a NeuroAI approach and draw inspiration from neural Reinforcement Learning to develop a derivative-free optimizer for training neural networks, Dopamine. Dopamine is developed for Weight Perturbation (WP) learning that exploits stochastic updating of weights towards optima. It achieves this by minimizing the regret, a form of Reward Prediction Error (RPE) between the expected outcome from the perturbed model and the actual outcome from the unperturbed model. We use this RPE to adjust the learning rate in the network (i.e., creating an adaptive learning rate strategy, similar to the role of dopamine in the brain). We tested the Dopamine optimizer for training multi-layered perceptrons for XOR tasks, and recurrent neural networks for chaotic time series forecasting. Dopamine-trained models demonstrate accelerated convergence and outperform standard WP, and give comparable performance to gradient-based algorithms, while consuming significantly less computation and memory. Overall, the Dopamine optimizer not only finds robust solutions and comparable performance to the state-of-the-art Machine Learning optimizers but is also neurobiologically more plausible.