The reinforcement metalearner as a biologically plausible meta-learning framework.
Tim VriensMattias HoranJacqueline P GottliebMassimo SilvettiPublished in: The Behavioral and brain sciences (2024)
We argue that the type of meta-learning proposed by Binz et al. generates models with low interpretability and falsifiability that have limited usefulness for neuroscience research. An alternative approach to meta-learning based on hyperparameter optimization obviates these concerns and can generate empirically testable hypotheses of biological computations.
Keyphrases