AI Paper Atlas

Research map / Multi-agent systems and games / Human-AI and goal-conditioned

Towards Deviation-Robust Agent Navigation via Perturbation-Aware Contrastive Learning

Bingqian Lin, Yanxin Long, Yi Zhu, Fengda Zhu, Xiaodan Liang, Qixiang Ye, Liang Lin

TPAMI 2023 · Multi-agent systems and games › Human-AI and goal-conditioned · approach: Vision-language navigation agents

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
train with PROPEREnvDropout · R2R Val UnseenSR (%): 52 -> 55Improved
train with PROPERRelGraph · R2R Val UnseenSR (%): 57 -> 58Improved
train with PROPERVLN BERT · R2R Test UnseenSR (%): 63 -> 63No clear effect
add progressive trajectory augmentation to teacher+RL (ablation)EnvDropout · R2R Val UnseenSR (%): 47.6 -> 50.4Improved
make perturbation augmentation progressive instead of non-progressive (ablation)EnvDropout · R2R Val UnseenSR (%): 49.2 -> 50.4Improved
add perturbation-aware contrastive learning (ablation)EnvDropout+Progressive Aug · R2R Val UnseenSR (%): 50.4 -> 51.3Improved
add perturbation-aware contrastive learning (ablation)EnvDropout+Progressive Aug · R2R Val SeenSR (%): 62.6 -> 63.3Improved
use Teacher2Student curriculum instead of teacher forcing only (ablation)EnvDropout · R2R Val UnseenSR (%): 42.9 -> 45.6Improved
train with PROPER, evaluated under perturbationEnvDropout · PP-R2R Val UnseenSR (%): 23.9 -> 30.3Improved
train with PROPER, evaluated under perturbationVLN BERT · PP-R2R Val UnseenSR (%): 38.8 -> 42.9Improved
evaluate under perturbation instead of perturbation-freeRelGraph · PP-R2R Val UnseenSR (%): 52.5 -> 27.5Hurt
add contrastive learning to perturbation-free plus perturbation-based training (ablation)EnvDropout · PP-R2R Val UnseenSR (%): 28.7 -> 30.3Improved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy