AI Paper Atlas

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

Self-Monitoring Navigation Agent via Auxiliary Progress Estimation

ICLR 2019 · Multi-agent systems and games › Human-AI and goal-conditioned · approach: Vision-language navigation agents · 185 citations (OpenAlex)

Read the paperCheck your idea against 108,967 papers

AI-extracted summary. Written by AI from the paper's title only (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
Replace the panoramic-action baseline with visual-textual co-grounding (ablation)VLN navigation agent · R2R validation-unseenSR: 0.27 -> 0.42Helped
Add progress monitoring to co-grounding with greedy decoding (ablation)Self-monitoring agent · R2R validation-unseenSR: 0.42 -> 0.44Helped
Add progress inference rather than greedy decoding (ablation)Co-grounding plus progress monitor · R2R validation-unseenSR: 0.44 -> 0.46Helped
Add a progress monitor to beam search (ablation)Co-grounding beam-search agent · R2R validation-unseenSR: 0.49 -> 0.57Helped
Use beam search instead of greedy decoding (ablation)Co-grounding-only agent · R2R validation-unseenSR: 0.42 -> 0.49Helped
Add speaker-generated data augmentationSelf-monitoring agent with beam search · R2R test-unseenSR: 0.57 -> 0.61Helped
Add speaker-generated data augmentation (ablation)Self-monitoring agent with beam search · R2R validation-seenSR: 0.70 -> 0.71Helped

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