AI Paper Atlas

Research map / Reinforcement learning / Visual and representation RL

No RL, No Simulation: Learning to Navigate without Navigating

Meera Hahn, Devendra Singh Chaplot, Shubham Tulsiani, Mustafa Mukadam, James Matthew Rehg, Abhinav Gupta

NeurIPS 2021 · Reinforcement learning › Visual and representation RL · approach: Vision-based robot RL · 7 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 predicted distance network G_D with ground truth (ablation)NRNS · Gibson Straight HardSuccess @1m: 23.45 -> 62.16Improved
replace predicted distance network G_D with ground truth (ablation)NRNS · Gibson Curved HardSuccess @1m: 12.50 -> 47.70Improved
replace predicted target network G_T with ground truth (ablation)NRNS · Gibson Straight HardSuccess @1m: 62.16 -> 95.91Improved
replace predicted exploration module G_EA with ground truth (ablation)NRNS · Gibson Straight HardSuccess @1m: 95.91 -> 100.00Improved
replace G_D with ground truth (ablation)NRNS · MP3D Straight HardSuccess @1m: 22.30 -> 58.40Improved
inject sensor and actuation noiseNRNS · Gibson Straight EasySuccess @1m: 68.00 -> 64.10Hurt
inject sensor and actuation noiseNRNS · Gibson Straight HardSuccess @1m: 23.82 -> 25.19Improved
use GRU memory instead of metric map in BCBC baseline · Gibson Straight EasySuccess @1m: 24.80 -> 34.90Improved
train RL with 5x data and 100M steps instead of 10M stepsRL baseline · Gibson Straight EasySuccess @1m: 10.50 -> 43.20Improved
NRNS vs best BC baselineNRNS · Gibson Straight EasySuccess @1m: 34.90 -> 68.00Improved
train NRNS on RealEstate10K instead of Gibson videosNRNS · Gibson Straight EasySuccess @1m: 68.00 -> 56.42Hurt
train NRNS on RealEstate10K instead of Gibson videosNRNS · Gibson Curved MediumSuccess @1m: 23.90 -> 12.90Hurt

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