{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,30]],"date-time":"2024-10-30T05:31:08Z","timestamp":1730266268129,"version":"3.28.0"},"reference-count":19,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2018,7]]},"DOI":"10.1109\/ijcnn.2018.8489655","type":"proceedings-article","created":{"date-parts":[[2018,10,19]],"date-time":"2018-10-19T22:25:09Z","timestamp":1539987909000},"page":"1-8","source":"Crossref","is-referenced-by-count":14,"title":["Comparing Multi-Armed Bandit Algorithms and Q-learning for Multiagent Action Selection: a Case Study in Route Choice"],"prefix":"10.1109","author":[{"given":"Thiago B. F.","family":"de Oliveira","sequence":"first","affiliation":[]},{"given":"Ana L. C.","family":"Bazzan","sequence":"additional","affiliation":[]},{"given":"Bruno C.","family":"da Silva","sequence":"additional","affiliation":[]},{"given":"Ricardo","family":"Grunitzki","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1287\/mnsc.17.11.712"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1016\/0041-1647(75)90030-1"},{"key":"ref12","article-title":"An iterative assignment approach to capacity restraint on arterial networks","volume":"347","author":"smock","year":"1962","journal-title":"Highway Research Board Bulletin"},{"key":"ref13","first-page":"199","article-title":"Stochastic Multi-ArmedBandit Problem with Non-stationary Rewards","author":"gur","year":"2014","journal-title":"Advances in Neural Information Processing Systems 27"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2015.2403288"},{"key":"ref15","article-title":"Decentralized Learning for Multiplayer Multi-armed Bandits","author":"kalathil","year":"2012","journal-title":"ArXiv e-prints"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ITA.2010.5454071"},{"key":"ref17","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)"},{"key":"ref18","first-page":"1","article-title":"Using topological statistics to bias and accelerate route choice: preliminary findings in synthetic and real-world road networks","author":"stefanello","year":"2016","journal-title":"Proc of the International Workshop on Agents in Traffic and Transportation"},{"key":"ref19","doi-asserted-by":"crossref","DOI":"10.1109\/IJCNN.2018.8489029","article-title":"Towards designing optimal reward functions in multi-agent reinforcement learning problems","author":"grunitzki","year":"2018","journal-title":"Proc of the 2018 International Joint Conference on Neural Networks (IJCNN 2018)"},{"key":"ref4","first-page":"1","article-title":"Algorithms for the multi-armed bandit problem","volume":"1","author":"kuleshov","year":"2010","journal-title":"Journal of Machine Learning"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1680\/ipeds.1952.11259"},{"key":"ref6","first-page":"174","article-title":"On upper-confidence bound policies for switching bandit problems","volume":"6925 lnai","author":"garivier","year":"2011","journal-title":"Lecture Notes in Computer Science (including subseries Lecture Notes in Artificial Intelligence and Lecture Notes in Bioinformatics)"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1023\/A:1013689704352"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1137\/S0097539701398375"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1093\/biomet\/25.3-4.285"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1002\/9781119993308"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.2016.7727899"},{"key":"ref9","first-page":"2249","article-title":"An Empirical Evaluation of Thompson Sampling","author":"chapelle","year":"2011","journal-title":"Advances in neural information processing systems"}],"event":{"name":"2018 International Joint Conference on Neural Networks (IJCNN)","start":{"date-parts":[[2018,7,8]]},"location":"Rio de Janeiro","end":{"date-parts":[[2018,7,13]]}},"container-title":["2018 International Joint Conference on Neural Networks (IJCNN)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8465565\/8488986\/08489655.pdf?arnumber=8489655","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2020,8,23]],"date-time":"2020-08-23T23:39:46Z","timestamp":1598225986000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8489655\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,7]]},"references-count":19,"URL":"https:\/\/doi.org\/10.1109\/ijcnn.2018.8489655","relation":{},"subject":[],"published":{"date-parts":[[2018,7]]}}}