A theoretical case-study of Scalable Oversight in Hierarchical Reinforcement Learning

Authors: Tom Yan, Zachary Lipton

NeurIPS 2024 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Theoretical A theoretical case-study of Scalable Oversight in Hierarchical Reinforcement Learning
Researcher Affiliation Academia Tom Yan, Zachary Lipton Machine Learning Department Carnegie Mellon University Pittsburgh, PA 15213 {tyyan, zlipton}@cmu.edu
Pseudocode Yes Algorithm 1 Hierarchical-UCB-VI (Hier-UCB-VI); Algorithm 2 Hierarchical-REGIME (Hier-REGIME)
Open Source Code No This is a theory paper that does not involve code.
Open Datasets No This is a theory paper that has no experiments section.
Dataset Splits No This is a theory paper that has no experiments section.
Hardware Specification No This is a theory paper that has no experiments section.
Software Dependencies No This is a theory paper that does not involve code.
Experiment Setup No This is a theory paper that has no experiments section.