AI Paper Atlas

Research map / Reinforcement learning / Visual and representation RL

Learning Object Relation Graph and Tentative Policy for Visual Navigation

Heming Du, Xin Yu, Liang Zheng

ECCV 2020 · Reinforcement learning › Visual and representation RL · approach: Vision-based robot RL · 141 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
add trial-driven IL (ablation)navigation network · AI2-Thor unseen scenes (ALL)success rate (%): 66.8% -> 69.3%Improved
add trial-driven IL (ablation)navigation network · AI2-Thor unseen scenes (ALL)SPL: 0.375 -> 0.394Improved
add ORG (ablation)navigation network · AI2-Thor unseen scenes (ALL)success rate (%): 67.5% -> 69.3%Improved
add ORG (ablation)navigation network · AI2-Thor unseen scenes (ALL)SPL: 0.345 -> 0.394Improved
add TPN (ablation)navigation network · AI2-Thor unseen scenes (ALL)success rate (%): 66.6% -> 69.3%Improved
add TPN (ablation)navigation network · AI2-Thor unseen scenes (ALL)SPL: 0.387 -> 0.394Improved
apply IL supervision at every step instead of only in deadlock (ablation)navigation network · AI2-Thor unseen scenes (ALL)success rate (%): 69.3% -> 47.7%Hurt
update navigation network via TPN at every state (ablation)navigation network · AI2-Thor unseen scenes (ALL)success rate (%): 69.3% -> 66.2%Hurt
replace TPN escape policy with random actions (ablation)navigation network · AI2-Thor unseen scenes (ALL)success rate (%): 69.3% -> 62.3%Hurt
add ORG to baselinebaseline · AI2-Thor unseen scenes (ALL)success rate (%): 56.4 -> 65.3Improved
add trial-driven IL to baselinebaseline · AI2-Thor unseen scenes (ALL)success rate (%): 56.4 -> 63.6Improved
add TPN to baselinebaseline · AI2-Thor unseen scenes (ALL)SPL: 0.319 -> 0.316No clear effect

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