MacMic: Executing Iceberg Orders via Hierarchical Reinforcement Learning

Authors: Hui Niu, Siyuan Li, Jian Li

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

Reproducibility Variable Result LLM Response
Research Type Experimental Comprehensive experimental results on 200 stocks across the US and China A-share markets validate the effectiveness of the proposed method.
Researcher Affiliation Academia Hui Niu 1 , Siyuan Li 2 and Jian Li 1 1Institute for Interdisciplinary Information Sciences, Tsinghua University, Beijing, China 2Faculty of Computing, Harbin Institute of Technology, Harbin, China
Pseudocode No The paper does not contain structured pseudocode or algorithm blocks.
Open Source Code No The paper does not provide any statement or link regarding the public availability of its source code.
Open Datasets No The paper states they collected data from '200 constituent stocks within two real-world stock indexes spanning both the Chinese and US markets' but does not provide concrete access information (link, DOI, repository, or formal citation) to their specific compiled dataset.
Dataset Splits No The paper states, 'For our experiments, 80% of the trading days are utilized as the training dataset, while the remaining 20% constitute the test dataset,' but does not mention a separate validation dataset split.
Hardware Specification No The paper does not provide specific hardware details (exact GPU/CPU models, processor types, or memory amounts) used for running its experiments.
Software Dependencies No The paper does not provide specific software dependencies or library versions needed to replicate the experiment.
Experiment Setup Yes The trading task is to sell the shares of 5% of the entire market trading volume of each asset during a 4-hour period following the market s opening every day, i.e., T = 240 minutes. The episode length of the high-level policy is H = 240, and the execution time for the low-level policy is t = 1 minute. Besides, we set np = 7 for the low-level policy.