# Active Inference in Hebbian Learning Networks

arXiv: https://arxiv.org/abs/2306.05053 · HTML: https://mlsanity.com/paper/2306.05053/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 11 of its 33 references that are in the map.
- First posted on arXiv 8 Jun 2023.

## Builds on (most cited first, 11 of 11)

- [OpenAI Gym](https://mlsanity.com/paper/1606.01540/) (2016)
- [Deep active inference agents using Monte-Carlo methods](https://mlsanity.com/paper/2006.04176/) (2020)
- [Deep Active Inference](https://mlsanity.com/paper/1709.02341/) (2017)
- [Unsupervised Learning by Competing Hidden Units](https://mlsanity.com/paper/1806.10181/) (2018)
- [Learning step sizes for unfolded sparse coding](https://mlsanity.com/paper/1905.11071/) (2019)
- [Can a Fruit Fly Learn Word Embeddings?](https://mlsanity.com/paper/2101.06887/) (2021)
- [Event-Driven Contrastive Divergence for Spiking Neuromorphic Systems](https://mlsanity.com/paper/1311.0966/) (2013)
- [Backprop-Free Reinforcement Learning with Active Neural Generative Coding](https://mlsanity.com/paper/2107.07046/) (2021)
- [Predictive Coding as a Neuromorphic Alternative to Backpropagation: A Critical Evaluation](https://mlsanity.com/paper/2304.02658/) (2023)
- [A New Look at Spike-Timing-Dependent Plasticity Networks for Spatio-Temporal Feature Learning](https://mlsanity.com/paper/2111.00791/) (2021)
- [Learning and Inference in Sparse Coding Models with Langevin Dynamics](https://mlsanity.com/paper/2204.11150/) (2022)

## Abstract (arXiv)

This work studies how brain-inspired neural ensembles equipped with local Hebbian plasticity can perform active inference (AIF) in order to control dynamical agents. A generative model capturing the environment dynamics is learned by a network composed of two distinct Hebbian ensembles: a posterior network, which infers latent states given the observations, and a state transition network, which predicts the next expected latent state given current state-action pairs. Experimental studies are conducted using the Mountain Car environment from the OpenAI gym suite, to study the effect of the various Hebbian network parameters on the task performance. It is shown that the proposed Hebbian AIF approach outperforms the use of Q-learning, while not requiring any replay buffer, as in typical reinforcement learning systems. These results motivate further investigations of Hebbian learning for the design of AIF networks that can learn environment dynamics without the need for revisiting past buffered experiences.