AI Paper Atlas

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

One Life to Learn: Inferring Symbolic World Models for Stochastic Environments from Unguided Exploration

Zaid Khan, Archiki Prasad, Elias Stengel-Eskin, Jaemin Cho, Mohit Bansal

ICLR 2026 · Multi-agent systems and games › Human-AI and goal-conditioned · approach: World-model-based agents · 8 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
add gradient-based parameter inference over law weights (ablation)OneLife · Crafter-OO (state ranking and fidelity)Rank@1: 13.0% -> 18.7%Improved
add gradient-based parameter inference over law weights (ablation)OneLife · Crafter-OO (state ranking and fidelity)MRR: 0.429 -> 0.479Improved
add gradient-based parameter inference over law weights (ablation)OneLife · Crafter-OO (state ranking and fidelity)normalized edit distance: 0.057 -> 0.058No clear effect
use OneLife inference instead of PoE-World inference (ablation)OneLife law synthesizer · Crafter-OO (state ranking and fidelity)Rank@1: 10.8% -> 18.7%Improved
use OneLife inference instead of PoE-World inference (ablation)OneLife law synthesizer · Crafter-OO (state ranking and fidelity)raw edit distance: 10.634 -> 8.764Improved
replace deterministic monolithic program synthesis with mixture of lawsWorldCoder vs OneLife · Crafter-OO (state ranking and fidelity)MRR: 0.264 -> 0.479Improved
optimize fidelity only (PoE-World) without state ranking (ablation)PoE-World · Crafter-OO (state ranking and fidelity)Rank@1 vs random: 8.5% -> 10.8%No clear effect
use learned world model for simulating plansOneLife · Zombie Fighter, Stone Miner, Sword Makerplan preference match with true env: 3 of 3 scenarios matchedImproved

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