SEGAC: Sample Efficient Generalized Actor Critic for the Stochastic On-Time Arrival Problem

This paper studies the problem in transportation networks and introduces a novel reinforcement learning-based algorithm, namely. Different from almost all canonical sota solutions, which are usually computationally expensive and lack generalizability to unforeseen destination nodes, segac offers the...

Full description

Saved in:
Bibliographic Details
Main Authors: GUO, Honglian, HE, Zhi, SHENG, Wenda, CAO, Zhiguang, ZHOU, Yingjie, GAO, Weinan
Format: text
Language:English
Published: Institutional Knowledge at Singapore Management University 2024
Subjects:
Online Access:https://ink.library.smu.edu.sg/sis_research/8704
https://ink.library.smu.edu.sg/context/sis_research/article/9707/viewcontent/T_ITS_SEGAC_final.pdf
Tags: Add Tag
No Tags, Be the first to tag this record!
Institution: Singapore Management University
Language: English
id sg-smu-ink.sis_research-9707
record_format dspace
spelling sg-smu-ink.sis_research-97072024-04-04T09:11:07Z SEGAC: Sample Efficient Generalized Actor Critic for the Stochastic On-Time Arrival Problem GUO, Honglian HE, Zhi SHENG, Wenda CAO, Zhiguang ZHOU, Yingjie GAO, Weinan This paper studies the problem in transportation networks and introduces a novel reinforcement learning-based algorithm, namely. Different from almost all canonical sota solutions, which are usually computationally expensive and lack generalizability to unforeseen destination nodes, segac offers the following appealing characteristics. segac updates the ego vehicle’s navigation policy in a sample efficient manner, reduces the variance of both value network and policy network during training, and is automatically adaptive to new destinations. Furthermore, the pre-trained segac policy network enables its real-time decision-making ability within seconds, outperforming state-of-the-art sota algorithms in simulations across various transportation networks. We also successfully deploy segac to two real metropolitan transportation networks, namely Chengdu and Beijing, using real traffic data, with satisfying results. 2024-01-01T08:00:00Z text application/pdf https://ink.library.smu.edu.sg/sis_research/8704 info:doi/10.1109/TITS.2024.3361445 https://ink.library.smu.edu.sg/context/sis_research/article/9707/viewcontent/T_ITS_SEGAC_final.pdf http://creativecommons.org/licenses/by-nc-nd/4.0/ Research Collection School Of Computing and Information Systems eng Institutional Knowledge at Singapore Management University Gaussian distribution Generalized actor critic Navigation Optimization Real-time systems Reliability Routing sample efficiency stochastic on-time arrival (SOTA) Transportation variance reduction Operations Research, Systems Engineering and Industrial Engineering Theory and Algorithms Transportation
institution Singapore Management University
building SMU Libraries
continent Asia
country Singapore
Singapore
content_provider SMU Libraries
collection InK@SMU
language English
topic Gaussian distribution
Generalized actor critic
Navigation
Optimization
Real-time systems
Reliability
Routing
sample efficiency
stochastic on-time arrival (SOTA)
Transportation
variance reduction
Operations Research, Systems Engineering and Industrial Engineering
Theory and Algorithms
Transportation
spellingShingle Gaussian distribution
Generalized actor critic
Navigation
Optimization
Real-time systems
Reliability
Routing
sample efficiency
stochastic on-time arrival (SOTA)
Transportation
variance reduction
Operations Research, Systems Engineering and Industrial Engineering
Theory and Algorithms
Transportation
GUO, Honglian
HE, Zhi
SHENG, Wenda
CAO, Zhiguang
ZHOU, Yingjie
GAO, Weinan
SEGAC: Sample Efficient Generalized Actor Critic for the Stochastic On-Time Arrival Problem
description This paper studies the problem in transportation networks and introduces a novel reinforcement learning-based algorithm, namely. Different from almost all canonical sota solutions, which are usually computationally expensive and lack generalizability to unforeseen destination nodes, segac offers the following appealing characteristics. segac updates the ego vehicle’s navigation policy in a sample efficient manner, reduces the variance of both value network and policy network during training, and is automatically adaptive to new destinations. Furthermore, the pre-trained segac policy network enables its real-time decision-making ability within seconds, outperforming state-of-the-art sota algorithms in simulations across various transportation networks. We also successfully deploy segac to two real metropolitan transportation networks, namely Chengdu and Beijing, using real traffic data, with satisfying results.
format text
author GUO, Honglian
HE, Zhi
SHENG, Wenda
CAO, Zhiguang
ZHOU, Yingjie
GAO, Weinan
author_facet GUO, Honglian
HE, Zhi
SHENG, Wenda
CAO, Zhiguang
ZHOU, Yingjie
GAO, Weinan
author_sort GUO, Honglian
title SEGAC: Sample Efficient Generalized Actor Critic for the Stochastic On-Time Arrival Problem
title_short SEGAC: Sample Efficient Generalized Actor Critic for the Stochastic On-Time Arrival Problem
title_full SEGAC: Sample Efficient Generalized Actor Critic for the Stochastic On-Time Arrival Problem
title_fullStr SEGAC: Sample Efficient Generalized Actor Critic for the Stochastic On-Time Arrival Problem
title_full_unstemmed SEGAC: Sample Efficient Generalized Actor Critic for the Stochastic On-Time Arrival Problem
title_sort segac: sample efficient generalized actor critic for the stochastic on-time arrival problem
publisher Institutional Knowledge at Singapore Management University
publishDate 2024
url https://ink.library.smu.edu.sg/sis_research/8704
https://ink.library.smu.edu.sg/context/sis_research/article/9707/viewcontent/T_ITS_SEGAC_final.pdf
_version_ 1814047471615082496