Learning to Bid in Repeated First-Price Auctions with Budgets
Authors: Qian Wang, Zongjun Yang, Xiaotie Deng, Yuqing Kong
ICML 2023 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | Finally, we complement the theoretical results with numerical experiments to confirm the effectiveness of our budget management policy. |
| Researcher Affiliation | Academia | 1Center on Frontiers of Computing Studies, School of Computer Science, Peking University, Beijing, China 2School of Electronics Engineering and Computer Science, Peking University, Beijing, China 3Center for Multi-Agent Research, Institute for AI, Peking University, Beijing, China. |
| Pseudocode | Yes | Algorithm 1 Bidding Algorithm for First-Price Auctions with Budgets under Full Information Feedback |
| Open Source Code | No | The paper does not provide any explicit statements about making its source code publicly available or provide a link to a code repository. |
| Open Datasets | No | The paper states: 'We generate the sequence of competing bids by sampling each dt i.i.d. from normal distribution N(0.4, 0.1).' and 'For the sequence of private values, we consider normal distribution, logarithmic normal distribution and uniform distribution respectively.' This indicates generated data for experiments, not a publicly available dataset with concrete access information. |
| Dataset Splits | No | The paper describes generating its own data for simulation but does not specify explicit train/validation/test dataset splits. It evaluates performance over a 'time horizon T' of simulation rounds. |
| Hardware Specification | No | The paper does not provide specific details about the hardware used to run the experiments (e.g., CPU, GPU models, memory, or cloud instance types). |
| Software Dependencies | No | The paper does not specify any software dependencies with version numbers (e.g., programming languages, libraries, or frameworks like Python, PyTorch, TensorFlow, etc.). |
| Experiment Setup | Yes | We consider repeated first-price auctions with T = 10^6 rounds, budget amount B = 10^4 and upper bound on values v = 1. ... For all algorithms, we uniformly set M = K = 100, failure probability δ = 0.01, and adopt fixed step size ϵ = 1/T. |