AI Paper Atlas

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

Intrinsically Motivated Goal Exploration Processes with Automatic Curriculum Learning

Sébastien Forestier, Rémy Portelas, Yoan Mollard, Pierre-Yves Oudeyer

JMLR 2022 · Multi-agent systems and games › Human-AI and goal-conditioned · approach: Intrinsically motivated exploration

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 modular (per-object) goal spaces instead of a flat goal space (ablation)IMGEP agent · 2D Simulated, Magnet Toolmedian exploration after 100k iterations: about 10% -> about 60%Improved
add modular goal spaces instead of flat goal space (ablation)IMGEP agent · Minecraft Mountain Cart, Pickaxemedian exploration: 15% -> 45%Improved
add modular goal spaces (ablation)IMGEP agent · Robotic environmentexploration of objects other than handImproved
add learning-progress-based goal space selection instead of random choice (AMB vs RMB) (ablation)Modular IMGEP · Minecraft Mountain Cart, Pickaxe competencemedian competence: 40 -> 45Improved
add learning-progress goal space selection instead of random (AMB vs RMB) (ablation)Modular IMGEP · Minecraft Mountain Cart, Cart competencemedian competence: 9 -> 11No clear effect
add learning-progress goal space selection (AMB vs RMB) (ablation)Modular IMGEP · 2D Simulated, Magnet Toolmedian exploration: 36 -> 61Improved
add learning-progress goal space selection (AMB vs RMB) (ablation)Modular IMGEP · Minecraft Mountain Cart, Cart spacemedian unique outcomes: 162 -> 360Improved
replace hand-engineered fixed curriculum with autonomous learning-progress curriculum (AMB vs FC) (ablation)Modular IMGEP · 2D Simulated, Magnet Toolmedian exploration: 67 -> 61No clear effect
replace fixed curriculum with AMB (ablation)Modular IMGEP · Minecraft Mountain Cart, Cart competencemedian competence: 17 -> 11No clear effect
replace fixed curriculum with AMB (ablation)Modular IMGEP · Robotic environment, right joystick and soundexplorationImproved
use only a single goal space (SGS) instead of AMB (ablation)Modular IMGEP · Minecraft Mountain Cart, Cart goalsmedian competence: 11 -> 0Hurt
use random policies instead of AMB (ablation)IMGEP agent · 2D Simulatedtouching toy with stickHurt

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