AI Paper Atlas

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

Control What You Can: Intrinsically Motivated Task-Planning Agent

Sebastian Blaes, Marin Vlastelica Pogančić, Jiajie Zhu, Georg Martius

NeurIPS 2019 · Multi-agent systems and games › Human-AI and goal-conditioned · approach: Intrinsically motivated exploration · 3 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 CWYC's learning-progress task selection, surprise-based exploration, and task planning instead of independent equal-allocation learningSAC and HIRO baselines · Synthetic tool-use environmentcontrol success rateImproved
Use CWYC's learned task planning and resource allocation instead of independent equal-allocation learningDDPG+HER baseline · Robotic manipulation environmentlearning speedImproved
Remove surprise detection (ablation)CWYC · Synthetic tool-use environmentcontrol success rateHurt
Add surprise detection (ablation)CWYC · Synthetic tool-use environmentcontrol success rateImproved
Replace learning-progress resource allocation with uniform task sampling (ablation)CWYC · Synthetic tool-use environmentlearning speedHurt

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