cs.FLNov 16, 2026

Tensorized Automata: Algebraically Informed Representation Learning for Sequential Decision Making

Authors: Anand Balakrishnan, Dweep Trivedi, Swarat Chaudhuri

Organizations: Department of Computer Science, University of Texas at Austin

Abstract

Task representations for sequential decision making should describe both an objective and progress toward it. We present an algebraically informed pipeline that uses the relational structure and language semantics of alternating finite automata (AFAs) to learn control features and compile compact execution operators. AND-OR message passing learns task and state vectors; selected configurations define an event-driven Boolean matrix operator. We prove that initial and successor language coverage make its carrier represent the exact residual after every prefix, with a sufficient capacity bound in terms of reachable configurations. Conjunction and disjunction use the same pipeline. Fidelity and composition audits evaluate copied formulas and learned disjunct assignments. In five-policy-seed XLand experiments with larger training pools, pooled execution-state vectors outperform raw carrier bits and task-blind conditioning across three task pools under two rejection rewards. They achieve 77.3% success on multi-event tasks and 99.4% on a four-task stratum with 33--128-state minimal DFAs, using 16 operator slots. LetterWorld results show useful residual conditioning alongside a remaining gap to RAD. These results connect algebraically informed representation learning to compact task execution and useful policy conditioning.

Figures & tables

Appendix figures & tables64 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. A Goal-Set Characterization of Task Composition in the Boolean Task Algebra

    Jun 2, 2026Eduardo Terrés-Caballero, Herke van HoofReinforcement LearningGoal-Conditioned RL