Giving Up Control: Neurons as Reinforcement Learning Agents

Abstract

Artificial Intelligence has historically relied on planning, heuristics, and handcrafted approaches designed by experts. All the while claiming to pursue the creation of Intelligence. This approach fails to acknowledge that intelligence emerges from the dynamics within a complex system. Neurons in the brain are governed by local rules, where no single neuron, or group of neurons, coordinates or controls the others. This local structure gives rise to the appropriate dynamics in which intelligence can emerge. Populations of neurons must compete with their neighbors for resources, inhibition, and activity representation. At the same time, they must cooperate, so the population and organism can perform high-level functions. To this end, we introduce modeling neurons as reinforcement learning agents. Where each neuron may be viewed as an independent actor, trying to maximize its own self-interest. By framing learning in this way, we open the door to an entirely new approach to building intelligent systems.

References in corpus (7)

• Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer
• Megatron-LM: Training Multi-Billion Parameter Language Models Using Model Parallelism
• Do ImageNet Classifiers Generalize to ImageNet?
• Deep Learning: A Critical Appraisal
• Towards Biologically Plausible Deep Learning
• Reinforcement Learning applied to Single Neuron
• Questions to Guide the Future of Artificial Intelligence Research

Cited by in corpus (2)

• The Sensory Neuron as a Transformer: Permutation-Invariant Neural Networks for Reinforcement Learning
• Collective Intelligence for Deep Learning: A Survey of Recent Developments