Probably Anytime-Safe Stochastic Combinatorial Semi-Bandits
Authors: Yunlong Hou, Vincent Y. F. Tan, Zixin Zhong
ICML 2023 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | Experiments are conducted to corroborate our theoretical findings. Our problem setup, the proposed PASCOMBUCB algorithm, and novel analyses are applicable to domains such as recommendation systems and transportation in which an agent is allowed to choose multiple items at a single time step and wishes to control the risk over the whole time horizon. |
| Researcher Affiliation | Academia | 1Department of Mathematics, National University of Singapore, Singapore 2Department of Electrical and Computer Engineering, National University of Singapore, Singapore 3Institute of Operations Research and Analytics, National University of Singapore, Singapore 4Department of Computing Science, University of Alberta, Canada. |
| Pseudocode | Yes | Algorithm 1 PASCOMBUCB |
| Open Source Code | Yes | Codes are accessible at https://github.com/Y-Hou/PASSCSB.git. |
| Open Datasets | No | The paper mentions "We design two instances where the rewards are Beta distributed with means and variances as in Table 1." This indicates a synthetic dataset created by the authors, but no access information (link, citation for public dataset, etc.) is provided for it to be publicly available. |
| Dataset Splits | No | The paper does not provide specific details on training, validation, or test splits. It only mentions designing instances and running experiments. |
| Hardware Specification | No | The paper does not mention any specific hardware used for running the experiments. |
| Software Dependencies | No | The paper does not mention any specific software dependencies with version numbers. |
| Experiment Setup | No | The paper mentions "confidence parameter δ = 0.05" and "time horizon T" but does not specify other experimental setup details such as learning rates, batch sizes, or optimizer settings, which would typically be included in a detailed experimental setup. |