Boosting Efficiency in Task-Agnostic Exploration through Causal Knowledge

Authors: Yupei Yang, Biwei Huang, Shikui Tu, Lei Xu

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

Reproducibility Variable Result LLM Response
Research Type Experimental Empirical experiments, on both synthetic data and realworld applications, further validate the benefits of causal exploration. The source code is available at https://github.com/CMACH508/Causal Exploration. (Abstract) ... To evaluate the effectiveness of causal exploration in complex scenarios, we conduct a series of experiments on both synthetic datasets and real-world applications, including the traffic light control task and Mu Jo Co control suites [Todorov et al., 2012]. (Section 6)
Researcher Affiliation Academia Yupei Yang1 , Biwei Huang2 , Shikui Tu1 and Lei Xu1,3 1Department of Computer Science and Engineering, Shanghai Jiao Tong University, China 2Halicio glu Data Science Institute (HDSI), University of California San Diego, USA 3Guangdong Institute of Intelligence Science and Technology, Zhuhai, China
Pseudocode Yes Algorithm 1 Task-agnostic Causal Exploration (Section 5, page 5)
Open Source Code Yes The source code is available at https://github.com/CMACH508/Causal Exploration. (Abstract)
Open Datasets No The paper refers to
Dataset Splits No The paper mentions a
Hardware Specification No The paper does not provide specific hardware details (e.g., GPU/CPU models, memory specifications) used for running its experiments.
Software Dependencies No The paper does not list specific software dependencies with version numbers.
Experiment Setup Yes Implementation details and more experimental results including the identified causal structures are given in Appendix D. (Section 6.1) ... We adopt the Adam optimizer with learning rate 3e-4, weight decay 1e-5. (Appendix D)