AI Paper Atlas

Research map / Multi-agent systems and games / Human-AI and goal-conditioned

Active Neural Localization

Devendra Singh Chaplot, Emilio Parisotto, Ruslan Salakhutdinov

ICLR 2018 · Multi-agent systems and games › Human-AI and goal-conditioned · approach: Imitation and skill learning · 54 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 learned active actions and a jointly trained neural localization model instead of passive Markov LocalizationMaze2D · Maze2D Allaccuracy: 0.483 -> 0.934Improved
Use learned active actions and a jointly trained neural localization model instead of Active Markov Localization (Slow)Maze2D · Maze2D Allaccuracy: 0.904 -> 0.934Improved
Use learned active actions and a jointly trained neural localization model instead of Active Markov Localization (Fast)Maze2D · Maze2D Allaccuracy: 0.571 -> 0.934Improved
Replace active Markov search with Active Neural LocalizationMaze2D · Maze2D Allruntime for 1000 episodes: 130.2 -> 62.0; 6527.8 -> 62.0Mixed
Use learned active actions and jointly learned perception instead of Markov Localization3D localization · Maze3D and Unreal3D Allaccuracy: 0.600 -> 0.826Improved
Use Active Neural Localization instead of Active Markov Localization (Slow)3D localization · Maze3D and Unreal3D Allaccuracy: 0.665 -> 0.826Improved
Use Active Neural Localization instead of Active Markov Localization (Fast)3D localization · Maze3D and Unreal3D Allaccuracy: 0.632 -> 0.826Improved
Use Active Neural Localization instead of the 3D Markov baseline3D localization · Maze3D and Unreal3D Allruntime for 1000 episodes: 2484.4 -> 905.9Improved
Train on random-texture Maze3D and transfer directly to Unreal3D without fine-tuningActive Neural Localization · Maze3D to Unreal3Daccuracy: 0.921Improved
Test the RGB-based model under changed lighting, using memory images captured with lights onActive Neural Localization · Unreal3D without lightsaccuracy: 0.934 -> 0.505Hurt
Evaluate on unseen maze layouts and textures, including the no-landmark settingActive Neural Localization · Maze3D unseen mazes, unseen textures, 0 landmarksaccuracy: 0.871Improved
Give the agent a longer episode to localizeActive Neural Localization · Maze2D 7x7accuracy: 0.936 -> 0.939Improved

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