by John Vastola Papers
3 papers found
Conference
Deep RL Needs Deep Behavior Analysis: Exploring Implicit Planning by Model-Free Agents in Open-Ended Environments
Riley Simmons-Edler, Ryan Badman, Felix Berg et al.
NEURIPS 2025oralarXiv:2506.06981
3
citations
Generalization through variance: how noise shapes inductive biases in diffusion models
John Vastola
ICLR 2025arXiv:2504.12532
18
citations
Gradient Descent as Loss Landscape Navigation: a Normative Framework for Deriving Learning Rules
John Vastola, Samuel J Gershman, Kanaka Rajan
NEURIPS 2025arXiv:2510.26997
1
citations