Notice: The reproducibility variables underlying each score are classified using an automated LLM-based pipeline, validated against a manually labeled dataset. LLM-based classification introduces uncertainty and potential bias; scores should be interpreted as estimates. Full accuracy metrics and methodology are described in [1].
Information Capacity Regret Bounds for Bandits with Mediator Feedback
Authors: Khaled Eldowa, Nicolò Cesa-Bianchi, Alberto Maria Metelli, Marcello Restelli
JMLR 2024 | Venue PDF | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Theoretical | We introduce the policy set capacity as an information-theoretic measure for the complexity of the policy set. Adopting the classical EXP4 algorithm, we provide new regret bounds depending on the policy set capacity in both the adversarial and the stochastic settings. For a selection of policy set families, we prove nearly-matching lower bounds, scaling similarly with the capacity. |
| Researcher Affiliation | Academia | Khaled Eldowa EMAIL Universit a degli Studi di Milano Milano, 20133, Italy Nicol o Cesa-Bianchi EMAIL Universit a degli Studi di Milano and Politecnico di Milano Milano, 20133, Italy Alberto Maria Metelli EMAIL Politecnico di Milano Milano, 20133, Italy Marcello Restelli EMAIL Politecnico di Milano Milano, 20133, Italy |
| Pseudocode | Yes | Algorithm 1 Exp4 (Fixed Policy Set) |
| Open Source Code | No | The paper does not explicitly provide concrete access to source code for the methodology described. |
| Open Datasets | No | The paper primarily deals with theoretical analysis of regret bounds and does not conduct experiments on specific datasets. |
| Dataset Splits | No | The paper does not use empirical datasets for experimentation, therefore, no dataset split information is provided. |
| Hardware Specification | No | The paper focuses on theoretical regret bounds and does not describe any experiments that would require hardware specifications. |
| Software Dependencies | No | The paper is theoretical and does not mention any specific software dependencies with version numbers required for implementation. |
| Experiment Setup | No | The paper is theoretical and discusses algorithmic parameters in the context of proving regret bounds, not as part of a concrete experimental setup with hyperparameters for implementation. |