Alexander Ilin

A Relational Model for One-Shot Classification

2021 · arXiv (Cornell University)

We show that a deep learning model with built-in relational inductive bias can bring benefits to sample-efficient learning, without relying on extensive data augmentation. The proposed one-shot classification model performs relational matching of a pair …

Adaptive Behavior Cloning Regularization for Stable Offline-to-Online Reinforcement Learning

2022

Offline reinforcement learning, by learning from a fixed dataset, makes it possible to learn agent behaviors without interacting with the environment. However, depending on the quality of the offline dataset, such pre-trained agents may have …