Research map / Vision-language and multimodal / Robot action and navigation
The Regretful Agent: Heuristic-Aided Navigation Through Progress Estimation
Check 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 changed | Where | Measured | Effect |
|---|---|---|---|
| add learned Regret Module and Progress Marker | Greedy VLN navigation · R2R Test (unseen) | SR: 0.43 -> 0.48 | Helped |
| add learned Regret Module and Progress Marker | Greedy VLN navigation · R2R Test (unseen) | SPL: 0.32 -> 0.40 | Helped |
| add learned Regret Module (ablation) | Regretful agent · R2R Validation-Unseen | SR: 0.44 -> 0.47 | Helped |
| add learned Regret Module (ablation) | Regretful agent · R2R Validation-Unseen | SPL: 0.32 -> 0.37 | Helped |
| add Progress Marker alongside Regret Module (ablation) | Regretful agent · R2R Validation-Unseen | SR: 0.47 -> 0.48 | Helped |
| add Progress Marker alongside Regret Module (ablation) | Regretful agent · R2R Validation-Unseen | SPL: 0.37 -> 0.37 | No clear effect |
| block rollback actions (ablation) | Regretful agent · R2R Validation-Unseen | SR: 0.48 -> 0.46 | Hurt |
| block rollback actions (ablation) | Regretful agent · R2R Validation-Unseen | SPL: 0.37 -> 0.41 | Helped |
| block rollback actions (ablation) | Self-Monitoring · R2R Validation-Unseen | SR: 0.44 -> 0.44 | No clear effect |
| train on synthetic rather than real data (ablation) | Regretful agent · R2R Validation-Unseen | SR: 0.48 -> 0.41 | Hurt |
| train on synthetic rather than real data (ablation) | Regretful agent · R2R Validation-Unseen | OSR: 0.61 -> 0.58 | Hurt |
Closest papers by meaning
- STRIDER: Navigation via Instruction-Aligned Structural Decision Space Optimization (NeurIPS 2025 · similarity 0.89)
- Towards Long-Horizon Vision-Language Navigation: Platform, Benchmark and Method (CVPR 2025 · similarity 0.88)
- NavGPT: Explicit Reasoning in Vision-and-Language Navigation with Large Language Models (AAAI 2024 · similarity 0.87)
- Active Test-time Vision-Language Navigation (NeurIPS 2025 · similarity 0.87)
- GoalLadder: Incremental Goal Discovery with Vision-Language Models (NeurIPS 2025 · similarity 0.87)
- Vision-Language Navigation with Energy-Based Policy (NeurIPS 2024 · similarity 0.87)
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.