AI Paper Atlas

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

Planning and Acting with Non-Deterministic Events: Navigating between Safe States

Lukas Chrpa, Jakub Gemrot, Martin Pilat

AAAI 2020 · Multi-agent systems and games › Human-AI and goal-conditioned · approach: World-model-based agents · 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
limit consecutive steps in unsafe states (LIMIT) vs dangerousness-based DANGPER replanning · Perestroika-5successful runs: 83 -> 100Improved
LIMIT vs DANGPER replanning · AUV-3successful runs: 80 -> 100Improved
LIMIT vs PER-APPPER replanning · Perestroika-5successful runs: 3 -> 100Improved
LIMIT vs PER-EVENTPER replanning · Perestroika-5successful runs: 1 -> 100Improved
LIMIT vs DANGPER replanning · Perestroika-5planning time (ms): 21479 -> 2198Improved
LIMIT vs DANGPER replanning · Perestroika-6planning time (ms): 14170 -> 633Improved
LIMIT vs DANGPER replanning · AUV-3planning time (ms): 1620 -> 2198Hurt
LIMIT vs DANGPER replanning · AUV-6planning time (ms): 2681 -> 6982Hurt
LIMIT vs DANGPER replanning · Perestroika-6actions: 111.78 -> 15.84Improved
LIMIT vs DANGPER replanning · AUV-1actions: 41.81 -> 38.60No clear effect
encode as FOND and use PRP strong cyclic planner instead of LIMITPRP · AUV-1solved problems: 987 secondsHurt

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