← Search

Maxwell Goldstein

2 accepted papers

2021

Automatic Data Augmentation for Generalization in Reinforcement Learning

NeurIPS 2021poster

Deep reinforcement learning (RL) agents often fail to generalize beyond their training environments. To alleviate this problem, recent work has proposed the use of data augmentation. However, different tasks tend to benefit from different types of augmentations and selecting the right one typically…

2018

PAC-Bayes Control: Synthesizing Controllers that Provably Generalize to Novel Environments

CoRL 2018

Our goal is to synthesize controllers for robots that provably generalize well to novel environments given a dataset of example environments. The key technical idea behind our approach is to leverage tools from generalization theory in machine learning by exploiting a precise analogy (which we prese