From Optimal Policies to Individual Differences: Rethinking Reinforcement Learning for Biology

2026/07/17 by Patrick Govoni, Palina Bartashevich, Clémence Bergerot +3
#cs.NE

paper · pdf

Abstract

Reinforcement learning (RL) is primarily known as a computational method for optimizing control tasks, but it is increasingly used to explain biological behavior. While RL successfully captures key aspects of biology, a major gap remains: between-agent behavioral variability. Consistent individual differences naturally permeate biological populations, yet RL models typically present only the single best individual or the population average. Addressing this gap requires moving beyond current practices to generate behavioral diversity using biologically plausible mechanisms. Here, we examine approaches from various subfields of RL and outline potential paths forward to close the gap between biology and simulation.

Citations

• Beyond networks: Toward adaptive models of biological complexity

Related

• Illuminating the Three Dogmas of Reinforcement Learning under Evolutionary Light
• The Evolution theory of Learning: From Natural Selection to Reinforcement Learning
• Of Mice and Machines: A Comparison of Learning Between Real World Mice and RL Agents
• Reinforcement Learning with Brain-Inspired Modulation can Improve Adaptation to Environmental Changes
• Resource-rational reinforcement learning and sensorimotor causal states, and resource-rational maximiners