Tag
An expository article exploring the lattice of sets of natural numbers under inclusion, discussing suborders like chains and copies of the integers, and highlighting the richness of the power set lattice.
This paper revisits the Boolean Task Algebra (BTA) for zero-shot task composition in reinforcement learning, proving that in deterministic MDPs all optimal extended Q-functions collapse to just two components (universal and empty tasks), making the originally proposed logarithmic base task set redundant. The authors introduce a goal-set-based composition method that reduces learning costs and composition time while preserving policy performance across multiple experimental domains.