mlsanityData to 14 Oct 2026

Generalisation to unseen topologies: Towards control of biological neural network activity

arXiv 2407.12789 ↗First posted 17 Jun 2024q-bio.NC cs.AI cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

Novel imaging and neurostimulation techniques open doors for advancements in closed-loop control of activity in biological neural networks. This would allow for applications in the investigation of activity propagation, and for diagnosis and treatment of pathological behaviour. Due to the partially observable characteristics of activity propagation, through networks in which edges can not be observed, and the dynamic nature of neuronal systems, there is a need for adaptive, generalisable control. In this paper, we introduce an environment that procedurally generates neuronal networks with different topologies to investigate this generalisation problem. Additionally, an existing transformer-based architecture is adjusted to evaluate the generalisation performance of a deep RL agent in the presented partially observable environment. The agent demonstrates the capability to generalise control from a limited number of training networks to unseen test networks.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 15 of its 55 references that are in the map. First posted on arXiv 17 Jun 2024.

Builds on

15 of 55 references.

References · 15

  1. 2017Attention Is All You Needcited by 60,361
  2. 2021Decision Transformer: Reinforcement Learning via Sequence Modelingcited by 1,546
  3. 2021Offline Reinforcement Learning as One Big Sequence Modeling Problemcited by 644
  4. 2023Retentive Network: A Successor to Transformer for Large Language Modelscited by 613
  5. 2019Leveraging Procedural Generation to Benchmark Reinforcement Learningcited by 483
  6. 2015Deep Recurrent Q-Learning for Partially Observable MDPscited by 465
  7. 2015Contextual Markov Decision Processescited by 220
  8. 2021A Survey of Zero-shot Generalisation in Deep Reinforcement Learningcited by 170
  9. 2022TransDreamer: Reinforcement Learning with Transformer World Modelscited by 143
  10. 2020My Body is a Cage: the Role of Morphology in Graph-Based Incompatible Controlcited by 70
  11. 2021The Sensory Neuron as a Transformer: Permutation-Invariant Neural Networks for Reinforcement Learningcited by 50
  12. 2016Small-World Brain Networks Revisitedcited by 16
3 more
  1. 2021Reinforcement Learning for Traffic Signal Control: Comparison with Commercial Systemscited by 5
  2. 2020Self-organization toward criticality by synaptic plasticitycited by 2
  3. 2023Theoretical foundations of studying criticality in the braincited by 1

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025From Black-Box to White-Box: Control-Theoretic Neural Network Interpretability
  2. 2025Graph Neural Network-Based Reinforcement Learning for Controlling Biological Networks - the GATTACA Framework
  3. 2024Growing Artificial Neural Networks for Control: the Role of Neuronal Diversity
  4. 2026NS-Copilot: An LLM-Driven Agent System for Autonomous Neuroscience Analysis
  5. 2024Biologically-Plausible Topology Improved Spiking Actor Network for Efficient Deep Reinforcement Learning
  6. 2025Neural cellular automata: applications to biology and beyond classical AI
  7. 2026PolyGLU: State-Conditional Activation Routing in Transformer Feed-Forward Networks
  8. 2024BLEND: Behavior-guided Neural Population Dynamics Modeling via Privileged Knowledge Distillation