NeurIPS - Measuring Visual Generalization in Continuous Control from Pixels

less than 1 minute read

Title: Measuring Visual Generalization in Continuous Control from Pixels

  • authors: Jake Grigsby, Yanjun Qi

Paper Arxiv

Code Here


Self-supervised learning and data augmentation have significantly reduced the performance gap between state and image-based reinforcement learning agents in continuous control tasks. However, it is still unclear whether current techniques can face a variety of visual conditions required by real-world environments. We propose a challenging benchmark that tests agents’ visual generalization by adding graphical variety to existing continuous control domains. Our empirical analysis shows that current methods struggle to generalize across a diverse set of visual changes, and we examine the specific factors of variation that make these tasks difficult. We find that data augmentation techniques outperform self-supervised learning approaches and that more significant image transformations provide better visual generalization \footnote{The benchmark and our augmented actor-critic implementation are open-sourced @ this https URL)


      title={Measuring Visual Generalization in Continuous Control from Pixels}, 
      author={Jake Grigsby and Yanjun Qi},

Support or Contact

Having trouble with our tools? Please contact Jake and we’ll help you sort it out.