Multi-task reinforcement learning in humans
| Autor: | Eric Schulz, Samuel J. Gershman, Momchil S. Tomov |
|---|---|
| Rok vydání: | 2021 |
| Předmět: |
0303 health sciences
Social Psychology Computer science business.industry Human intelligence Experimental and Cognitive Psychology Machine learning computer.software_genre Task (project management) 03 medical and health sciences Behavioral Neuroscience 0302 clinical medicine Reinforcement learning Artificial intelligence business computer 030217 neurology & neurosurgery 030304 developmental biology Standard model (cryptography) |
| Zdroj: | Nature Human Behaviour |
| ISSN: | 2397-3374 |
| DOI: | 10.1038/s41562-020-01035-y |
| Popis: | The ability to transfer knowledge across tasks and generalize to novel ones is an important hallmark of human intelligence. Yet not much is known about human multi-task reinforcement learning. We study participants’ behavior in a novel two-step decision making task with multiple features and changing reward functions. We compare their behavior to two state-of-the-art algorithms for multi-task reinforcement learning, one that maps previous policies and encountered features to new reward functions and one that approximates value functions across tasks, as well as to standard model-based and model-free algorithms. Across three exploratory experiments and a large preregistered experiment, our results provide strong evidence for a strategy that maps previously learned policies to novel scenarios. These results enrich our understanding of human reinforcement learning in complex environments with changing task demands. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|
Full text from SpringerLink