Uniform Last-Iterate Guarantee for Bandits and Reinforcement Learning

Authors: Junyan Liu, Yunfan Li, Ruosong Wang, Lin Yang

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

Reproducibility Variable Result LLM Response
Research Type Theoretical This paper is theoretically oriented and does not conduct any experiment.
Researcher Affiliation Academia Junyan Liu University of Washington junyanl1@cs.washington.edu Yunfan Li University of California, Los Angeles yunfanli@g.ucla.edu Ruosong Wang CFCS and School of Computer Science Peking University ruosongwang@pku.edu.cn Lin F. Yang University of California, Los Angeles linyang@ee.ucla.edu
Pseudocode Yes Algorithm 1 Elimination framework for ULI Algorithm 2 PE with adaptive barycentric spanner Algorithm 3 Tabular Episodic MDPs with ULI guarantee Algorithm 4 Uniform estimation for value functions Algorithm 5 Construct estimated value function
Open Source Code No The paper does not provide an explicit statement about open-source code release for the methodology described, nor does it provide a specific repository link. The NeurIPS checklist indicates "NA" for code access, stating "This paper is theoretically oriented and does not conduct any experiment.".
Open Datasets No The paper is theoretical and does not perform experiments with datasets, thus no training dataset information is provided.
Dataset Splits No The paper is theoretical and does not perform experiments, thus no dataset split information for training, validation, or testing is provided.
Hardware Specification No The paper is theoretical and does not involve computational experiments, thus no hardware specifications are provided.
Software Dependencies No The paper is theoretical and does not describe computational experiments or their software dependencies with version numbers.
Experiment Setup No The paper is theoretical and does not include an experimental setup with specific hyperparameters or training configurations.