← Mouhssine Rifaki

Research

Working papers

  1. Partner UED for cooperative multi-agent learning.

    in preparation·with Eugene Vinitsky·EMERGE Lab·2026

    We treat unsupervised environment design as a problem over partner policies in cooperative multi-agent learning, rather than over level layouts. The adversary samples co-players from a learned population, and the ego learns to coordinate with whatever partner it draws. We compare planning-based and policy-gradient adversaries against a domain-randomization baseline, then ask whether the limit in this regime comes from the search procedure or from the partner-pool formulation itself. The answer should not depend on which cooperative benchmark we run on.

  2. Finite-size scaling of Schelling-type segregation.

    in preparation·2026

    We perform a finite-size scaling study of the Schelling segregation model and its multi-radius generalizations. We measure critical exponents at four radii on lattices up to 2048 x 2048, verify universality across radii, and demonstrate hyperscaling through data collapse. The result establishes a noise floor for the order parameter and clarifies which earlier claims survive at large n.

  3. Adaptive sensing driven by prediction error.

    in preparation·with Amin Arbabian·Arbabian Lab, Stanford EE·2026

    We decompose the prediction error of a frozen-encoder world model into three additive terms: model floor, online noise gain, and event mass, and gate an expensive classifier on the residual. The detector ties a constant-velocity Kalman on bouncing balls and reaches 94 percent of every-frame accuracy at one-quarter compute on tracking clips, with the online noise estimate generalizing to real Big Buck Bunny scene cuts.

Publications

Forthcoming.