Arguably, the problem of learning represents a gateway to understanding intelligence in brains and machines, to discovering how the human brain works and to making intelligent machines that learn from ...

This repo contains a set of environments (based on OpenAI Gym and Roboschool), designed for evaluating generalization in reinforcement learning. We also include implementations of several deep ...

1 Department of Brain and Cognitive Sciences, Massachusetts Institute of Technology, Cambridge, MA, United States 2 Department of Neuroscience, Georgetown University Medical Center, Washington, DC, ...

This paper revisits the robust overfitting phenomenon of adversarial training. Observing that models with better robust generalization performance are less certain in predicting adversarially ...