Measuring Visual Generalization in Continuous Control from Pixels

October 13, 2020 ยท Entered Twilight ยท ๐Ÿ› arXiv.org

๐ŸŒ… TWILIGHT: Old Age
Predates the code-sharing era โ€” a pioneer of its time

"Last commit was 5.0 years ago (โ‰ฅ5 year threshold)"

Evidence collected by the PWNC Scanner

Repo contents: LICENSE, README.md, dmc_remastered, misc, mujoco.md, requirements.txt, setup.py

Authors Jake Grigsby, Yanjun Qi arXiv ID 2010.06740 Category cs.LG: Machine Learning Cross-listed cs.AI, cs.CV, cs.RO Citations 27 Venue arXiv.org Repository https://github.com/QData/dmc_remastered โญ 20 Last Checked 1 month ago
Abstract
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 @ https://github.com/QData/dmc_remastered)
Community shame:
Not yet rated
Community Contributions

Found the code? Know the venue? Think something is wrong? Let us know!

๐Ÿ“œ Similar Papers

In the same crypt โ€” Machine Learning