SOURCE-LINKED INTELLIGENCE

Large Discrete Policy: Advancing Explicit Behavior Modeling with Stochastic Iterative Scoring

arXiv · AI, language, vision and robotics · article · Sep 7, 2026 · UTC

Behavior policies are often formulated as continuous generative models, whose iterative denoising processes are expressive but difficult to interpret and prone to producing implausible actions. We propose the Large Discrete Policy (LDiP), a fully discrete behavior modeling framework that selects actions from a large vocabulary of physically plausible candidates. Rather than perturbing actions, LDiP improves expressivity through stochastic iterative scoring: it progressively re-scores and prunes candidates with score-space stochasticity, enabling fine-grained ranking and exploration among plaus

Read original source ↗ Open in workspace

recordType

paper

region

Global