{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,7,27]],"date-time":"2025-07-27T07:37:17Z","timestamp":1753601837325,"version":"3.28.0"},"reference-count":39,"publisher":"IEEE","license":[{"start":{"date-parts":[[2020,7,1]],"date-time":"2020-07-01T00:00:00Z","timestamp":1593561600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2020,7,1]],"date-time":"2020-07-01T00:00:00Z","timestamp":1593561600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2020,7,1]],"date-time":"2020-07-01T00:00:00Z","timestamp":1593561600000},"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":[[2020,7]]},"DOI":"10.1109\/ijcnn48605.2020.9207403","type":"proceedings-article","created":{"date-parts":[[2020,9,30]],"date-time":"2020-09-30T00:40:33Z","timestamp":1601426433000},"page":"1-9","source":"Crossref","is-referenced-by-count":1,"title":["On the Role of Reward Functions for Reinforcement Learning in the Traffic Assignment Problem"],"prefix":"10.1109","author":[{"given":"Ricardo","family":"Grunitzki","sequence":"first","affiliation":[]},{"given":"Gabriel","family":"de Oliveira Ramos","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CEC.2012.6256507"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1287\/mnsc.17.11.712"},{"key":"ref33","first-page":"2190","article-title":"Reward Design via Online Gradient Ascent","author":"sorg","year":"2010","journal-title":"Advances in Neural Information Processing Systems 23"},{"key":"ref32","first-page":"1281","article-title":"Intrinsically motivated reinforcement learning","volume":"17","author":"singh","year":"2004","journal-title":"Advances in Neural Information Processing Systems 17 (NIPS 2004)"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TAMD.2010.2051031"},{"key":"ref30","first-page":"2601","article-title":"Where do rewards come from","author":"singh","year":"2009","journal-title":"Proceedings of the Annual Conference of the Cognitive Science Society"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992698"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1145\/1329125.1329434"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4419-8909-3_1"},{"journal-title":"Reinforcement Learning An Introduction","year":"2018","author":"sutton","key":"ref34"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2013.2255286"},{"key":"ref11","article-title":"Combining car-to-infrastructure communication and multi-agent reinforcement learning in route choice","author":"grunitzki","year":"2016","journal-title":"Proceedings of the Ninth Workshop on Agents in Traffic and Transportation (ATT-2016)"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/BRACIS.2017.19"},{"key":"ref13","first-page":"1559","article-title":"A flexible approach for designing optimal reward functions","author":"grunitzki","year":"2017","journal-title":"Proceedings of the 16th International Conference on Autonomous Agents and Multiagent Systems (AAMAS 2017)"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/BRACIS.2014.53"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1162\/evco.2007.15.1.1"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1016\/0041-1647(75)90030-1"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TAMD.2014.2362682"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-25808-9_4"},{"key":"ref19","first-page":"278","article-title":"Policy invariance under reward transformations: Theory and application to reward shaping","author":"ng","year":"1999","journal-title":"Proceedings of the Sixteenth International Conference on Machine Learning"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1145\/279943.279964"},{"key":"ref4","first-page":"112","article-title":"Intrinsically motivated learning of hierarchical collections of skills","author":"barto","year":"2004","journal-title":"Proc 3rd Int Conf Development Learn"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.2018.8489029"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1016\/j.trb.2009.11.004"},{"journal-title":"Bureau of Public Roads Traffic Assignment Manual","year":"1964","key":"ref6"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1016\/j.trc.2017.08.019"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.2016.7727899"},{"key":"ref8","first-page":"746","article-title":"The dynamics of reinforcement learning in cooperative multiagent systems","author":"claus","year":"1998","journal-title":"Proceedings of the Fifteenth National Conference on Artificial Intelligence"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TSMCC.2007.913919"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/1007352.1007367"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1016\/j.trb.2006.02.008"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/1082473.1082486"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1287\/trsc.18.2.185"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1002\/9781119993308"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TAMD.2010.2051436"},{"key":"ref24","article-title":"A Budged-Balanced Tolling Scheme for Efficient Equilibria under Heterogeneous Preferences","author":"ramos","year":"2019","journal-title":"Proceedings of the Adaptive Learning Agents Workshop 2019 (ALA-19)"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC.2014.6958095"},{"key":"ref26","first-page":"56","article-title":"An improved learning automata approach for the route choice problem","author":"ramos","year":"2015","journal-title":"Agent Technology for Intelligent Mobile Services and Smart Societies"},{"key":"ref25","first-page":"846","article-title":"Learning to minimise regret in route choice","author":"ramos","year":"2017","journal-title":"Proc of the 16th International Conference on Autonomous Agents and Multiagent Systems (AAMAS 2017)"}],"event":{"name":"2020 International Joint Conference on Neural Networks (IJCNN)","start":{"date-parts":[[2020,7,19]]},"location":"Glasgow, United Kingdom","end":{"date-parts":[[2020,7,24]]}},"container-title":["2020 International Joint Conference on Neural Networks (IJCNN)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9200848\/9206590\/09207403.pdf?arnumber=9207403","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,6,28]],"date-time":"2022-06-28T21:53:14Z","timestamp":1656453194000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9207403\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,7]]},"references-count":39,"URL":"https:\/\/doi.org\/10.1109\/ijcnn48605.2020.9207403","relation":{},"subject":[],"published":{"date-parts":[[2020,7]]}}}