[2510.12088] One Life to Learn: Inferring Symbolic World Models for Stochastic Environments from Unguided Exploration

Computer Science > Artificial Intelligence arXiv:2510.12088 (cs) [Submitted on 14 Oct 2025 (v1), last revised 8 Apr 2026 (this version, v2)] Title:One Life to Learn: Inferring Symbolic World Models for Stochastic Environments from Unguided Exploration Authors:Zaid Khan, Archiki Prasad, Elias Stengel-Eskin, Jaemin Cho, Mohit Bansal View a PDF of the paper titled One Life to Learn: Inferring Symbolic World Models for Stochastic Environments from Unguided Exploration, by Zaid Khan and 4 other authors View PDF HTML (experimental) Abstract:Symbolic world modeling requires inferring and representing an environment's transitional dynamics as an executable program. Prior work has focused on largely deterministic environments with abundant interaction data, simple mechanics, and human guidance. We address a more realistic and challenging setting, learning in a complex, stochastic environment where the agent has only "one life" to explore a hostile environment without human guidance. We introduce OneLife, a framework that models world dynamics through conditionally-activated programmatic laws within a probabilistic programming framework. Each law operates through a precondition-effect structure, activating in relevant world states. This creates a dynamic computation graph that routes inference and optimization only through relevant laws, avoiding scaling challenges when all laws contribute to predictions about a complex, hierarchical state, and enabling the learning of stochastic dy...