Sample-Efficiency in Multi-Batch Reinforcement Learning: The Need for Dimension-Dependent Adaptivity

Authors: Emmeran Johnson, Ciara Pike-Burke, Patrick Rebeschini

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

Reproducibility Variable Result LLM Response
Research Type Theoretical We theoretically explore the relationship between sample-efficiency and adaptivity in reinforcement learning.
Researcher Affiliation Academia Emmeran Johnson & Ciara Pike-Burke Department of Mathematics, Imperial College London, United Kingdom {emmeran.johnson17,c.pike-burke}@imperial.ac.uk Patrick Rebeschini Department of Statistics, University of Oxford, United Kingdom patrick.rebeschini@stats.ox.ac.uk
Pseudocode Yes Algorithm 1 Multi-Batch Learning Model
Open Source Code No The paper does not mention or provide access to open-source code for its methodology. It is a theoretical paper.
Open Datasets No The paper is theoretical and does not use or refer to publicly available datasets for experiments.
Dataset Splits No The paper is theoretical and does not include experimental data splits.
Hardware Specification No The paper is theoretical and does not describe any experimental hardware used.
Software Dependencies No The paper is theoretical and does not mention specific software dependencies or versions.
Experiment Setup No The paper is theoretical and does not include details on experimental setup or hyperparameters.