AI Paper Atlas

Research map / Reinforcement learning / Visual and representation RL

What Matters in RL-Based Methods for Object-Goal Navigation? An Empirical Study and A Unified Framework

Hongze Wang, Boyang Sun, Jiaxu Xing, Fan Yang, Marco Hutter, Dhruv Shah, Davide Scaramuzza, Marc Pollefeys

ECCV 2026 · Reinforcement learning › Visual and representation RL · approach: Vision-based robot RL · 4 citations (OpenAlex)

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
use Gibson-finetuned Mask R-CNN instead of default checkpoint (ablation)Corner goal policy · Gibson valSR (%): 77.7 -> 83.8Improved
use fine-tuned Mask R-CNN instead of default (ablation)Frontier policy · Gibson valSR (%): 71.2 -> 79.9Improved
use newer detectors (YOLO11-XL, RF-DETR) instead of default Mask R-CNN (ablation)Corner goal policy · Gibson valSR (%): 77.7 -> 76.0 (YOLO11-XL), 77.6 (RF-DETR-Seg); SPL 40.9 -> 44.2Mixed
enlarge local map from 240 to 480 (ablation)Corner goal policy · Gibson valSR (%): 78.7 -> 83.8Improved
enlarge local map from 240 to 480 (ablation)Frontier policy · Gibson valSR (%): 79.6 -> 79.9; D-SR 61.0 -> 57.2No clear effect
add map augmentation (ablation)Corner goal policy · Gibson valD-SR (%): 63.5 -> 69.5Improved
add map augmentation (ablation)Corner goal policy · Gibson valSR (%): 83.3 -> 83.8No clear effect
compress 20-channel semantic map into 3-channel RGB observation (ablation)RL discrete policy · Gibson valSR (%): 83.4 -> 83.8No clear effect
use continuous instead of discrete action space (ablation)RL policy · Gibson valSPL (%): 43.3 -> 48.2Improved
replace CNN with Transformer backbone (ablation)RL discrete policy · Gibson valSR (%): 83.7 -> 83.8No clear effect
use reward 1 (distance to target) instead of reward 2 (ablation)RL discrete policy · Gibson valSPL (%): 43.3 -> 45.8; SR 83.8 -> 85.2Improved
add untrapping helper (ablation)RL continuous policy · Gibson valSR (%): 81.3 -> 84.4Improved

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