Pinductor uses LLM priors to learn POMDP world models with 330x fewer episodes than DreamerV3

burny_tech · x · 2026-09-29

Accepted at NeurIPS 2026, 'Learning POMDP World Models from Observations with Language-Model Priors' (arXiv 2605.13740) — by Bernhard Schölkopf, Philipp Hennig, Lancelot Da Costa et al. — introduces Pinductor: an LLM proposes candidate POMDP world models from a few observation-action trajectories and iteratively refines them against a belief-based likelihood score.

Original post →

More from Embodied

Embodied channel →