AI Paper Atlas

Research map / Reinforcement learning / Visual and representation RL

Symmetry-aware Neural Architecture for Embodied Visual Navigation

Shuang Liu, Masanori Suganuma, Takayuki Okatani

IJCV 2023 · Reinforcement learning › Visual and representation RL · approach: Robust visual encoders for RL · 14 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
replace global policy with symmetry-aware network (G-convolution, blur pooling, SGPP)ANS · MP3D (trained on Gibson)area coverage (m^2): 76.3 -> 84.4Improved
replace global policy with symmetry-aware networkANS · Gibson (trained on Gibson)area coverage (m^2): 32.9 -> 33.7Improved
replace global policy with symmetry-aware networkANS · MP3D (trained on MP3D)area coverage (m^2): 80.8 -> 86.2Improved
replace global policy with symmetry-aware networkANS · Gibson (trained on MP3D)area coverage (m^2)No clear effect
learn RL policy over frontiers (FBE-RL) instead of heuristic FBEFBE · Gibsonarea coverage (m^2): 26.5 -> 28.2Improved
learn RL policy over frontiers (FBE-RL) instead of heuristic FBEFBE · MP3D (trained on Gibson)area coverage (m^2): 69.6 -> 63.0Hurt
add SGPP critic on top of G-conv and blur pooling (S-ANS vs E-ANS) (ablation)S-ANS · Gibson and MP3D (trained on Gibson)area coverage (m^2): ranking S-ANS > E-ANSImproved
use global average pooling (G-ANS) instead of no pooling invariance (E-ANS) in critic (ablation)E-ANS · Gibson and MP3D (trained on Gibson)area coverage (m^2): ranking E-ANS > G-ANSHurt
add G-convolution and blur pooling to ANS (G-ANS vs ANS) (ablation)ANS · Gibson and MP3D (trained on Gibson)area coverage (m^2): ranking G-ANS > ANSImproved
add symmetry-aware design to criticANS · Gibson (critic rotation std)std of critic output (lower better): 0.115 -> 0.078Improved

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