Reward magnitude determines reinforcement learning efficiency
- 1Mechanistic Cognitive Neuroscience, Janelia Research Campus of the Howard Hughes Medical Institute, Ashburn, VA, USA
Abstract
Standard animal learning studies minimize individual reward magnitudes to maximize the repetitions of reinforced behaviors. We investigated how reward magnitude influences initial learning across five behavioral paradigms in naïve mice. Especially large rewards could substantially improve learning efficiency through dissociable effects on within- and across-session learning and task engagement. The duration and magnitude of ventral striatal dopamine release scaled with reward sizes, and prolonged optogenetic enhancement of dopamine reward responses also reproduced much, but not all, of the benefits to learning produced by outsized rewards. These findings indicate that the reinforcement learning efficiency of animals has traditionally been underestimated and that dopamine signaling of rewards mediates task engagement in proportion to absolute reward magnitude.
Related
- Reward Prediction-Error Fidelity: a testable hypothesis linking reinforcement learning mechanisms to applied behavior analysis for autism and neurodevelopmental conditions.
- Volitional control of a recurrent brain computer interface via covert reinforcement of endogenous reward networks
- Probing biomarkers and clinical utility of reward learning across species using the Probabilistic Reward Task: 20 years of findings
- Punishment Enhances Reward Learning through Striatal Prediction Errors
- Trait anxiety selectively amplifies reward learning under uncertainty, while N3 sleep attenuates it
BibTeX
@article{gong2026reward,
title = {{Reward magnitude determines reinforcement learning efficiency}},
author = {Sheng Gong and Alyssa Martell and Joshua Tate Dudman and Luke T. Coddington},
journal = {Science},
year = {2026},
month = may,
doi = {10.1126/science.aeb0813},
url = {https://doi.org/10.1126/science.aeb0813},
note = {CC BY},
}
RIS
TY - JOUR
TI - Reward magnitude determines reinforcement learning efficiency
AU - Sheng Gong
AU - Alyssa Martell
AU - Joshua Tate Dudman
AU - Luke T. Coddington
PY - 2026
DA - 2026/05/21
JO - Science
DO - 10.1126/science.aeb0813
UR - https://doi.org/10.1126/science.aeb0813
AB - Standard animal learning studies minimize individual reward magnitudes to maximize the repetitions of reinforced behaviors. We investigated how reward magnitude influences initial learning across five behavioral paradigms in naïve mice. Especially large rewards could substantially improve learning efficiency through dissociable effects on within- and across-session learning and task engagement. The duration and magnitude of ventral striatal dopamine release scaled with reward sizes, and prolonged optogenetic enhancement of dopamine reward responses also reproduced much, but not all, of the benefits to learning produced by outsized rewards. These findings indicate that the reinforcement learning efficiency of animals has traditionally been underestimated and that dopamine signaling of rewards mediates task engagement in proportion to absolute reward magnitude.
SN - 0036-8075
SN - 0193-4511
SN - 1095-9203
ER -