# Meta-brain Models: biologically-inspired cognitive agents

arXiv: https://arxiv.org/abs/2109.11938 · HTML: https://mlsanity.com/paper/2109.11938/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 8 of its 78 references that are in the map.
- First posted on arXiv 31 Aug 2021.

## Builds on (most cited first, 8 of 8)

- [Multi-Agent Reinforcement Learning: A Selective Overview of Theories and Algorithms](https://mlsanity.com/paper/1911.10635/) (2019)
- [Neurosymbolic AI: The 3rd Wave](https://mlsanity.com/paper/2012.05876/) (2020)
- [Learning Latent Representations to Influence Multi-Agent Interaction](https://mlsanity.com/paper/2011.06619/) (2020)
- [Embodied Evolution in Collective Robotics: A Review](https://mlsanity.com/paper/1709.08992/) (2017)
- [Braitenberg Vehicles as Developmental Neurosimulation](https://mlsanity.com/paper/2003.07689/) (2020)
- [Connectionism, Complexity, and Living Systems: a comparison of Artificial and Biological Neural Networks](https://mlsanity.com/paper/2103.15553/) (2021)
- [Enaction-Based Artificial Intelligence: Toward Coevolution with Humans in the Loop](https://mlsanity.com/paper/1402.6663/) (2014)
- [Continual Developmental Neurosimulation Using Embodied Computational Agents](https://mlsanity.com/paper/2103.05753/) (2021)

## Built on by (most cited first, 1 of 1)

- [Layers, Folds, and Semi-Neuronal Information Processing](https://mlsanity.com/paper/2208.06382/) (2022)

## Abstract (arXiv)

Artificial Intelligence (AI) systems based solely on neural networks or symbolic computation present a representational complexity challenge. While minimal representations can produce behavioral outputs like locomotion or simple decision-making, more elaborate internal representations might offer a richer variety of behaviors. We propose that these issues can be addressed with a computational approach we call meta-brain models. Meta-brain models are embodied hybrid models that include layered components featuring varying degrees of representational complexity. We will propose combinations of layers composed using specialized types of models. Rather than using a generic black box approach to unify each component, this relationship mimics systems like the neocortical-thalamic system relationship of the mammalian brain, which utilizes both feedforward and feedback connectivity to facilitate functional communication. Importantly, the relationship between layers can be made anatomically explicit. This allows for structural specificity that can be incorporated into the model's function in interesting ways. We will propose several types of layers that might be functionally integrated into agents that perform unique types of tasks, from agents that simultaneously perform morphogenesis and perception, to agents that undergo morphogenesis and the acquisition of conceptual representations simultaneously. Our approach to meta-brain models involves creating models with different degrees of representational complexity, creating a layered meta-architecture that mimics the structural and functional heterogeneity of biological brains, and an input/output methodology flexible enough to accommodate cognitive functions, social interactions, and adaptive behaviors more generally. We will conclude by proposing next steps in the development of this flexible and open-source approach.