# A memory-based active inference model of DishBrain-like adaptive behaviour

arXiv: https://arxiv.org/abs/2508.06980 · HTML: https://mlsanity.com/paper/2508.06980/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 17 of its 40 references that are in the map.
- First posted on arXiv 9 Aug 2025.

## Builds on (most cited first, 17 of 17)

- [ChatGPT: Jack of all trades, master of none](https://mlsanity.com/paper/2302.10724/) (2023)
- [Active inference on discrete state-spaces: a synthesis](https://mlsanity.com/paper/2001.07203/) (2020)
- [Deep active inference agents using Monte-Carlo methods](https://mlsanity.com/paper/2006.04176/) (2020)
- [On the Relationship Between Active Inference and Control as Inference](https://mlsanity.com/paper/2006.12964/) (2020)
- [The free energy principle made simpler but not too simple](https://mlsanity.com/paper/2201.06387/) (2022)
- [Learning Perception and Planning with Deep Active Inference](https://mlsanity.com/paper/2001.11841/) (2020)
- [Branching Time Active Inference: the theory and its generality](https://mlsanity.com/paper/2111.11107/) (2021)
- [On efficient computation in active inference](https://mlsanity.com/paper/2307.00504/) (2023)
- [Branching Time Active Inference: empirical study and complexity class analysis](https://mlsanity.com/paper/2111.11276/) (2021)
- [Active Inference for Stochastic Control](https://mlsanity.com/paper/2108.12245/) (2021)
- [Active inference, Bayesian optimal design, and expected utility](https://mlsanity.com/paper/2110.04074/) (2021)
- [Designing explainable artificial intelligence with active inference: A framework for transparent introspection and decision-making](https://mlsanity.com/paper/2306.04025/) (2023)
- [Pattern recognition in the nucleation kinetics of non-equilibrium self-assembly](https://mlsanity.com/paper/2207.06399/) (2022)
- [Active Inference and Intentional Behaviour](https://mlsanity.com/paper/2312.07547/) (2023)
- [On Predictive planning and counterfactual learning in active inference](https://mlsanity.com/paper/2403.12417/) (2024)
- [Graph-Based Representation Learning of Neuronal Dynamics and Behavior](https://mlsanity.com/paper/2410.00665/) (2024)
- [Biological Neurons Compete with Deep Reinforcement Learning in Sample Efficiency in a Simulated Gameworld](https://mlsanity.com/paper/2405.16946/) (2024)

## Abstract (arXiv)

Recent and rapid advances in artificial intelligence (AI) make it increasingly important to understand the foundations of adaptive behaviour in autonomous agents, especially for building safe and efficient systems. While artificial neural networks have dominated the development of AI, recent work has begun to explore living biological neuronal networks as an alternative substrate for computation. These systems promise remarkable data and sample efficiency and rich dynamics, and may also inspire explainable and biologically plausible models. Here, we develop an experiment-informed active inference framework to model decision-making in closed-loop agents that mirror experimental setups using biological neurons. Using a generative model whose dimensions are matched to an experiment protocol, we systematically compare three decision-making schemes within this common generative model. Under matched episode counts (i.e. total data available for learning) to the in-vitro experiment, our simulations show that agents with short memory horizons reach a level of performance close to that of mouse and human cortical cultures (DishBrain platform), whereas longer memory horizons depart from it substantially. Increasing the planning horizon, by contrast, confers no comparable benefit. Because all model parameters are explicit, we can also track the quantities in our generative model that accompany this improvement, such as the risk term and the entropy of the transition and state-action mappings. Together, these results illustrate how active inference offers a formal language for comparing decision-making schemes in similar closed-loop control environments.