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:1908.06976 , year=
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.LG 2years
2026 2verdicts
UNVERDICTED 2roles
background 1polarities
background 1representative citing papers
Survey mapping RL techniques onto LLM training and highlighting gaps in value-based, off-policy, and bootstrapping methods.
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.
-
Modularized Reinforcement Learning on LLMs: From MDP Creation to Exploration and Learning
Survey mapping RL techniques onto LLM training and highlighting gaps in value-based, off-policy, and bootstrapping methods.