United States Department of Transportation
A Multiobjective Reinforcement Learning Framework for Equitable Toll Design on Express Lanes
File Language:
English
Details
-
Creators:
-
Corporate Creators:
-
Corporate Publisher:
-
Corporate Contributors:
-
Subject/TRT Terms:
-
Publication/ Report Number:
-
Resource Type:
-
Geographical Coverage:
-
Edition:Final Report: Jun 2023 - Dec 2023
-
Description:Express lanes are commonly used to mitigate traffic congestion by providing reliable travel time in exchange for tolls. However, there is a lack of guidance on designing equitable discounts for low-income travelers, creating barriers to equitable transportation systems. The past study on "Equitable Dynamic Pricing for Express Lanes "addressed some of these gaps by providing guidance for differential tolls and analyzing unintended traffic patterns. However, the framework was limited for single-objective optimization of equity. Furthermore, limitations on open-source algorithms for equity optimization hinder accessibility for researchers and practitioners. This project develops a reinforcement-learning-based optimization of express lane discounts considering reinforcement learning frameworks and creates an open-source tool for making previous research findings more accessible. In this research, the team has (a) designed an open-source platform that integrates advances in reinforcement learning literature for designing discounts for express lanes, and (b) tested the usefulness of the designed tools across multiple datasets and development platforms. The research findings indicate that traffic operations for express lanes are multi-objective in nature and require intentional tradeoffs between conflicting objectives such as maximizing equitable benefits and/or improving revenue.
-
Format:
-
Funding:
-
Download URL:
-
File Type:
[PDF - 1.41 MB] -
Collection(s):
-
Main Document Checksum:urn:sha-512:6ef83a3bff6b4992cdb8eb7198f422f0ad4b1981a877d37d9c7d677e551ade0367530c3630d5d6297477f5e72da03fd5e8c515c778bd4f9ff650d4d66b4295ee
File Language:
English
Found an issue?
ROSA P serves as an archival repository of USDOT-published products including scientific
findings, journal articles, guidelines, recommendations, or other information authored or co-authored by
USDOT or funded partners. As a repository, ROSA P retains documents in their original published format to
ensure public access to scientific information.
You May Also Like
COLLECTION
University Transportation Centers