A hierarchical RL-OC method uses inverse optimization to derive structured lower-level policies from demonstrations, claiming superior efficiency and quality over end-to-end RL and existing hierarchical baselines on two control tasks.
arXiv preprint arXiv:2405.13509 , year=
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Hierarchical Decision Making with Structured Policies: A Principled Design via Inverse Optimization
A hierarchical RL-OC method uses inverse optimization to derive structured lower-level policies from demonstrations, claiming superior efficiency and quality over end-to-end RL and existing hierarchical baselines on two control tasks.