← 研踪 PaperTrailarXiv:2611.21514 · v1
Tensorized Automata: Algebraically Informed Representation Learning for Sequential Decision Making
首次提交 2026-11-17 02:09
版本更新 2026-11-17 02:09
雷达观测 2026-11-17 16:10
摘要
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.
作者备注:This manuscript is an extended version of the paper submitted to L4DC 2027
观测到的版本
相邻记录可能跳过中间版本;首次发现 v2 及以上也会标为版本更新。
v1 · 2026-11-17 02:09 · 最新观测版本
Tensorized Automata: Algebraically Informed Representation Learning for Sequential Decision Making
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.
查看此版本解读 →查看此版本原文 ↗