{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,17]],"date-time":"2026-03-17T08:28:02Z","timestamp":1773736082661,"version":"3.50.1"},"reference-count":25,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,11,18]],"date-time":"2025-11-18T00:00:00Z","timestamp":1763424000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,11,18]],"date-time":"2025-11-18T00:00:00Z","timestamp":1763424000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,11,18]]},"DOI":"10.1109\/itsc60802.2025.11423037","type":"proceedings-article","created":{"date-parts":[[2026,3,16]],"date-time":"2026-03-16T20:10:23Z","timestamp":1773691823000},"page":"4181-4188","source":"Crossref","is-referenced-by-count":0,"title":["Energy-Aware Bus Speed Control via Proximal Policy Optimization: A Comparative Study Under Fixed-Time, Bus-Priority, and Backpressure Signal Control Strategies"],"prefix":"10.1109","author":[{"given":"Siyuan","family":"Huang","sequence":"first","affiliation":[{"name":"Piedmont Hills High School,San Jose,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xianyue","family":"Peng","sequence":"additional","affiliation":[{"name":"University of California, Davis,Dept. of Civil and Environmental Engineering,Davis,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Michael","family":"Zhang","sequence":"additional","affiliation":[{"name":"University of California, Davis,Dept. of Civil and Environmental Engineering,Davis,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/0377-2217(80)90126-5"},{"key":"ref2","first-page":"567","article-title":"Dynamic bus speed optimization using reinforcement learning","volume":"111","author":"Wang","year":"2020","journal-title":"Transportation Research Part C: Emerging Technologies"},{"key":"ref3","first-page":"102938","article-title":"Real-time traffic signal control with connected vehicles: A deep reinforcement learning approach","volume":"117","author":"Chen","year":"2016","journal-title":"Transportation Research Part C: Emerging Technologies"},{"issue":"12","key":"ref4","first-page":"4128","article-title":"Reinforcement learning for predictive traffic signal control","volume":"19","author":"Alesiani","year":"2018","journal-title":"IEEE Transactions on Intelligent Transportation Systems"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2022.3145798"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/VPPC55846.2022.10003458"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2023.3283617"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1016\/j.eng.2022.07.019"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TTE.2022.3185215"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1016\/j.jclepro.2024.141721"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.3390\/en15165878"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1016\/j.jclepro.2021.129031"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1016\/j.trc.2018.12.018"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1016\/j.energy.2020.117297"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1177\/09544070221103392"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1016\/j.energy.2022.124105"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1016\/j.jpowsour.2022.231099"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1561\/2200000071"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2017.2743240"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/GlobalSIP.2018.8646405"},{"key":"ref21","volume-title":"Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor","volume":"abs\/1801.01290","author":"Haarnoja","year":"2018"},{"key":"ref22","first-page":"10","article-title":"RLlib: Abstractions for distributed reinforcement learning","volume-title":"Proceedings of the 35th International Conference on Machine Learning","volume":"80","author":"Liang","year":"2018"},{"key":"ref23","volume-title":"SUMO-RL","author":"Alegre","year":"2019"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.5555\/2188385.2188395"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.5220\/0007364701340144"}],"event":{"name":"2025 IEEE 28th International Conference on Intelligent Transportation Systems (ITSC)","location":"Gold Coast, Australia","start":{"date-parts":[[2025,11,18]]},"end":{"date-parts":[[2025,11,21]]}},"container-title":["2025 IEEE 28th International Conference on Intelligent Transportation Systems (ITSC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11422813\/11423000\/11423037.pdf?arnumber=11423037","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,17]],"date-time":"2026-03-17T06:18:23Z","timestamp":1773728303000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11423037\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11,18]]},"references-count":25,"URL":"https:\/\/doi.org\/10.1109\/itsc60802.2025.11423037","relation":{},"subject":[],"published":{"date-parts":[[2025,11,18]]}}}