Reinforcement Causal Structure Learning on Order Graph
Authors: Dezhi Yang, Guoxian Yu, Jun Wang, Zhengtian Wu, Maozu Guo
AAAI 2023 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | Experiments on synthetic and benchmark datasets show that RCL-OG provides accurate posterior probability approximation and achieves better results than competitive causal discovery algorithms. |
| Researcher Affiliation | Academia | 1School of Software, Shandong University, Jinan, China 2SDU-NTU Joint Centre for AI Research, Shandong University, Jinan, China 3School of Electronic and Information Engineering, Suzhou University of Science and Technology, Suzhou, China 4College of Elec. & Inf. Eng., Beijing University of Civil Engineering and Architecture, Beijing, China |
| Pseudocode | Yes | Algorithm 1 RCL-OG: Reinforcement Causal Structure Learning on Order Graph |
| Open Source Code | Yes | The code of RCL-OG is shared at www.sduidea.cn/codes.php?name=RCL-OG. |
| Open Datasets | Yes | We evaluated RCL-OG on real-world flow cytometry data (Sachs et al. 2005) to learn a protein signaling causal network based on expression levels of proteins and phospholipids. |
| Dataset Splits | No | The paper describes generating synthetic data with 200 samples and using real-world data with 853 samples, but it does not specify any training, validation, or test dataset splits (e.g., percentages, sample counts, or cross-validation setup). |
| Hardware Specification | No | The paper states, 'We use Python 3.9 with the Mind Spore deep learning framework to implement RCLOG and perform experiment...', but it does not provide any specific hardware details such as GPU/CPU models, processor types, or memory specifications used for running the experiments. |
| Software Dependencies | No | The paper mentions 'We use Python 3.9 with the Mind Spore deep learning framework to implement RCLOG,' specifying a Python version, but it does not provide version numbers for the Mind Spore framework or any other key software dependencies or libraries. |
| Experiment Setup | Yes | Input: Observed data X Rn d, ϵ-greedy parameter ϵ, number of iterations τ, number of variables m and batch size z |