The reviewed record of science sign in
Pith

arxiv: 2010.06740 · v2 · pith:NVSZEEZZ · submitted 2020-10-13 · cs.LG · cs.AI· cs.CV· cs.RO

Measuring Visual Generalization in Continuous Control from Pixels

Reviewed by Pith T0 review T1 audit T2 compute T3 formal T4 kernel pith:NVSZEEZZrecord.jsonopen to challenge →

classification cs.LG cs.AIcs.CVcs.RO
keywords visualcontinuouscontrolgeneralizationlearningagentsaugmentationbenchmark
0
0 comments X
read the original 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)

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 1 Pith paper

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. From Pixels to Temporal Correlations: Learning Informative Representations for Reinforcement Learning Pre-training

    cs.LG 2026-07 unverdicted novelty 5.0

    MTCL learns multi-scale temporal correlations in videos via contrastive learning to produce more informative representations that improve sample efficiency and performance in downstream RL tasks.