Online Learning of Optimal Bidding Strategy in Repeated Multi-Commodity Auctions
Authors: M. Sevi Baltaoglu, Lang Tong, Qing Zhao
NeurIPS 2017 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | We evaluate the performance of DPDS empirically in the context of virtual trading in wholesale electricity markets by using historical data from the New York market. Empirical results show that DPDS consistently outperforms benchmark heuristic methods that are derived from machine learning and online learning approaches. |
| Researcher Affiliation | Academia | Sevi Baltaoglu Cornell University Ithaca, NY 14850 msb372@cornell.edu Lang Tong Cornell University Ithaca, NY 14850 lt35@cornell.edu Qing Zhao Cornell University Ithaca, NY 14850 qz16@cornell.edu |
| Pseudocode | Yes | Vn(j B/αt) = ( 0 if n = 0, j {0, 1, ..., αt}, max 0 i j (ˆrt,n(i B/αt) + Vn 1((j i)B/αt)) if 1 n K, j {0, 1, ..., αt}. (9) |
| Open Source Code | No | The paper does not provide any links to source code or explicitly state that their code is open-source or publicly available. |
| Open Datasets | Yes | New York ISO (NYISO), which consists of 11 zones, allows virtual transactions at zonal nodes only. So, we use historical DA and RT prices of these zones from 2011 to 2016 [30]. [30] NYISO Website, 2017. http://www.nyiso.com/public/markets_operations/market_data/pricing_data/index.jsp. |
| Dataset Splits | No | The paper describes using data from the previous year for training and the current year for testing, but it does not explicitly specify train/validation/test splits, percentages, or absolute sample counts for each split. |
| Hardware Specification | No | The paper does not provide any specific details about the hardware (e.g., GPU/CPU models, memory) used for running its experiments. |
| Software Dependencies | No | The paper refers to algorithms and techniques like 'SVM' and 'Kiefer-Wolfowitz stochastic approximation method' but does not specify any software dependencies with version numbers (e.g., Python, PyTorch, TensorFlow, or specific libraries with versions). |
| Experiment Setup | Yes | The algorithm parameter of DPDS was set as αt = t; and the step size at and ct of SA were set as 20000/t and 2000/t1/4, respectively. |