Objective-aware Traffic Simulation via Inverse Reinforcement Learning

Authors: Guanjie Zheng, Hanyang Liu, Kai Xu, Zhenhui Li

IJCAI 2021 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental Extensive experiments on synthetic and real-world datasets show the superior performance of our approach compared to state-of-the-art methods and its robustness to variant dynamics of traffic.
Researcher Affiliation Collaboration 1Shanghai Jiao Tong University 2Washington University in St. Louis 3Shanghai Tianrang Intelligent Technology Co., Ltd 4The Pennsylvania State University
Pseudocode Yes Algorithm 1: Training procedure of PS-AIRL
Open Source Code No The paper does not provide any statement or link regarding the availability of open-source code for the methodology described.
Open Datasets No We evaluate our proposed model on 3 different real-world traffic trajectory datasets with distinct road network structures collected from Hangzhou of China, and Los Angeles of US, including 3 typical 4-way intersections, a 4 4 network, and a 1 4 arterial network. See Appendix for details. The appendix will be released on the authors website and arxiv. The paper mentions specific datasets used but does not provide a direct link, DOI, or explicit citation for public access within the provided text. The appendix is mentioned as being released externally, which is not concrete access within the paper itself.
Dataset Splits No The paper mentions evaluating models on datasets but does not specify training, validation, or test dataset splits (e.g., percentages or sample counts).
Hardware Specification No The paper does not provide any specific details about the hardware (e.g., GPU/CPU models, memory, or cloud instances) used for running the experiments.
Software Dependencies No The paper mentions tools like SUMO, AIMSUN, MITSIM, and TRPO but does not provide specific version numbers for these or any other software dependencies.
Experiment Setup No The paper states, 'See Appendix for details' regarding data and experiment settings. While it mentions the use of TRPO as a policy optimizer and changes in simulation dynamics for robustness testing, it does not provide specific hyperparameters (e.g., learning rate, batch size) or detailed training configurations for its proposed PS-AIRL model within the main text.