Towards Tight Bounds on the Sample Complexity of Average-reward MDPs

Authors: Yujia Jin, Aaron Sidford

ICML 2021 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Theoretical We prove new upper and lower bounds for sample complexity of finding an ϵ-optimal policy of an infinite-horizon average-reward Markov decision process (MDP) given access to a generative model.
Researcher Affiliation Academia Yujia Jin 1 Aaron Sidford 1 1Management Science and Engineering, Stanford University, CA, United States. Correspondence to: Yujia Jin <yujiajin@stanford.edu>.
Pseudocode No The paper describes algorithms but does not include any structured pseudocode or algorithm blocks.
Open Source Code No The paper is purely theoretical and does not describe software or methodology for which open-source code would be provided.
Open Datasets No The paper is theoretical and does not conduct experiments on datasets, so there is no mention of publicly available or open datasets.
Dataset Splits No The paper is theoretical and does not conduct experiments on datasets, so there is no mention of training/validation/test splits.
Hardware Specification No The paper is purely theoretical and does not describe any experimental setup or hardware used.
Software Dependencies No The paper is purely theoretical and does not describe any experimental setup or software dependencies with versions.
Experiment Setup No The paper is purely theoretical and does not describe an experimental setup with hyperparameters or system-level training settings.