A Goal-Set Characterization of Task Composition in the Boolean Task Algebra 事件

A Goal-Set Characterization of Task Composition in the Boolean Task Algebra arXiv:2606.04053v1 Announce Type: cross Abstract: The Boolean Task Algebra (BTA) provides a principled framework for zero-shot task composition in reinforcement learning by equipping goal-reaching tasks with Boolean operations. We revisit its structural assumptions and formalize a collapse in the space of optimal extended Q-value functions: in deterministic MDPs, every such function is fully determined by the universal