Harnessing Density Ratios for Online Reinforcement Learning

Authors: Philip Amortila, Dylan J Foster, Nan Jiang, Ayush Sekhari, Tengyang Xie

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

Reproducibility Variable Result LLM Response
Research Type Theoretical While our results are theoretical in nature, we are optimistic that they will lead to further investigation into the power of density ratio modeling in online RL and inspire practical algorithms.
Researcher Affiliation Collaboration Philip Amortila UIUC Dylan J. Foster Microsoft Research Nan Jiang UIUC Ayush Sekhari MIT Tengyang Xie Microsoft Research
Pseudocode Yes Algorithm 1 GLOW: Global Optimism via Weight Function Realizability
Open Source Code No The paper does not provide an explicit statement about open-sourcing the code for the described methodology or a link to a code repository.
Open Datasets No The paper presents theoretical results and algorithms (GLOW, HYGLOW, H2O) and does not involve empirical evaluation on datasets. Therefore, it does not mention dataset availability for training.
Dataset Splits No The paper is theoretical and does not report on empirical experiments with datasets. Therefore, it does not provide information about training/validation/test dataset splits.
Hardware Specification No The paper is theoretical and does not conduct empirical experiments, therefore no hardware specifications are mentioned.
Software Dependencies No The paper is theoretical and does not describe any experimental implementation details that would require specific software dependencies with version numbers.
Experiment Setup No The paper is theoretical and does not describe an experimental setup with specific hyperparameters or training configurations for empirical evaluation.