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 →
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.
Forward citations
Cited by 1 Pith paper
-
From Pixels to Temporal Correlations: Learning Informative Representations for Reinforcement Learning Pre-training
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.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.