{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,8]],"date-time":"2025-09-08T05:36:36Z","timestamp":1757309796557,"version":"3.40.3"},"publisher-location":"Cham","reference-count":58,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031562549"},{"type":"electronic","value":"9783031562556"}],"license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024]]},"DOI":"10.1007\/978-3-031-56255-6_1","type":"book-chapter","created":{"date-parts":[[2024,3,29]],"date-time":"2024-03-29T11:01:47Z","timestamp":1711710107000},"page":"3-29","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Fair Deep Reinforcement Learning with\u00a0Generalized Gini Welfare Functions"],"prefix":"10.1007","author":[{"given":"Guanbao","family":"Yu","sequence":"first","affiliation":[]},{"given":"Umer","family":"Siddique","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2008-4569","authenticated-orcid":false,"given":"Paul","family":"Weng","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,3,30]]},"reference":[{"key":"1_CR1","unstructured":"Agarwal, A., Beygelzimer, A., Dud\u00edk, M., Langford, J., Wallach, H.: A reductions approach to fair classification. In: International Conference on Machine Learning, pp. 60\u201369. PMLR (2018)"},{"key":"1_CR2","doi-asserted-by":"publisher","first-page":"543","DOI":"10.1016\/j.endm.2013.05.136","volume":"41","author":"E Amaldi","year":"2013","unstructured":"Amaldi, E., Coniglio, S., Gianoli, L.G., Ileri, C.U.: On single-path network routing subject to max-min fair flow allocation. Electron. Notes Discrete Math. 41, 543\u2013550 (2013)","journal-title":"Electron. Notes Discrete Math."},{"issue":"1","key":"1_CR3","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s10458-021-09533-7","volume":"36","author":"X Bei","year":"2022","unstructured":"Bei, X., Liu, S., Poon, C.K., Wang, H.: Candidate selections with proportional fairness constraints. Auton. Agent. Multi-Agent Syst. 36(1), 1\u201332 (2022)","journal-title":"Auton. Agent. Multi-Agent Syst."},{"issue":"5","key":"1_CR4","doi-asserted-by":"publisher","first-page":"591","DOI":"10.1007\/s10458-019-09417-x","volume":"33","author":"A Beynier","year":"2019","unstructured":"Beynier, A., et al.: Local envy-freeness in house allocation problems. Auton. Agent. Multi-Agent Syst. 33(5), 591\u2013627 (2019)","journal-title":"Auton. Agent. Multi-Agent Syst."},{"key":"1_CR5","doi-asserted-by":"crossref","unstructured":"Brams, S.J., Taylor, A.D.: Fair Division: From Cake-Cutting to Dispute Resolution. Cambridge University Press, Cambridge, March 1996","DOI":"10.1017\/CBO9780511598975"},{"key":"1_CR6","doi-asserted-by":"crossref","unstructured":"Brams, S.J., Taylor, A.D.: Fair Division: From Cake-Cutting to Dispute Resolution. Cambridge University Press, Cambridge (1996)","DOI":"10.1017\/CBO9780511598975"},{"key":"1_CR7","unstructured":"Busa-Fekete, R., Sz\u00f6r\u00e9nyi, B., Weng, P., Mannor, S.: Multi-objective bandits: Optimizing the generalized GINI index. In: International Conference on Machine Learning, pp. 625\u2013634. PMLR (2017)"},{"issue":"6","key":"1_CR8","doi-asserted-by":"publisher","first-page":"1016","DOI":"10.1111\/j.1523-1739.2012.01951.x","volume":"26","author":"I Chad\u00e8s","year":"2012","unstructured":"Chad\u00e8s, I., Curtis, J.M., Martin, T.G.: Setting realistic recovery targets for two interacting endangered species, sea otter and northern abalone. Conserv. Biol. 26(6), 1016\u20131025 (2012)","journal-title":"Conserv. Biol."},{"issue":"3","key":"1_CR9","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3457166","volume":"9","author":"M Chakraborty","year":"2021","unstructured":"Chakraborty, M., Igarashi, A., Suksompong, W., Zick, Y.: Weighted envy-freeness in indivisible item allocation. ACM Trans. Econ. Comput. (TEAC) 9(3), 1\u201339 (2021)","journal-title":"ACM Trans. Econ. Comput. (TEAC)"},{"key":"1_CR10","doi-asserted-by":"crossref","unstructured":"Chen, J., Wang, Y., Lan, T.: Bringing fairness to actor-critic reinforcement learning for network utility optimization. In: INFOCOM (2021)","DOI":"10.1109\/INFOCOM42981.2021.9488823"},{"key":"1_CR11","first-page":"3","volume":"30","author":"Y Chevaleyre","year":"2006","unstructured":"Chevaleyre, Y., Dunne, P.E., Lema\u00eetre, M., Maudet, N., Padget, J., Phelps, S., Rodr\u00edguez-aguilar, J.A.: Issues in multiagent resource allocation. Computer 30, 3\u201331 (2006)","journal-title":"Computer"},{"key":"1_CR12","unstructured":"Chierichetti, F., Kumar, R., Lattanzi, S., Vassilvitskii, S.: Fair clustering through fairlets. In: Advances in Neural Information Processing Systems, vol. 30. Curran Associates, Inc. (2017)"},{"key":"1_CR13","doi-asserted-by":"crossref","unstructured":"Choquet, G.: Theory of capacities. In: Annales de l\u2019institut Fourier, vol. 5, pp. 131\u2013295 (1954)","DOI":"10.5802\/aif.53"},{"key":"1_CR14","unstructured":"Chow, Y., Ghavamzadeh, M.: Algorithms for CVaR optimization in MDPs (2014)"},{"key":"1_CR15","first-page":"16610","volume":"34","author":"C Cousins","year":"2021","unstructured":"Cousins, C.: An axiomatic theory of provably-fair welfare-centric machine learning. Adv. Neural. Inf. Process. Syst. 34, 16610\u201316621 (2021)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"1_CR16","doi-asserted-by":"crossref","unstructured":"de la Cruz, G., Peng, B., Lasecki, W.S., Taylor, M.E.: Generating real-time crowd advice to improve reinforcement learning agents. In: AAAI Workshop Learning for General Competency in Video Games, pp. 17\u201320 (2015)","DOI":"10.1145\/2732158.2732180"},{"key":"1_CR17","doi-asserted-by":"crossref","unstructured":"Do, V., Usunier, N.: Optimizing generalized GINI indices for fairness in rankings. In: Proceedings of the 45th International ACM SIGIR Conference on Research and Development in Information Retrieval, pp. 737\u2013747 (2022)","DOI":"10.1145\/3477495.3532035"},{"key":"1_CR18","doi-asserted-by":"crossref","unstructured":"Dwork, C., Hardt, M., Pitassi, T., Reingold, O., Zemel, R.: Fairness through awareness. In: Proceedings of the 3rd Innovations in Theoretical Computer Science Conference, pp. 214\u2013226, January 2012","DOI":"10.1145\/2090236.2090255"},{"key":"1_CR19","unstructured":"Ghalme, G., Nair, V., Patil, V., Zhou, Y.: Long-term resource allocation fairness in average markov decision process (AMDP) environment. In: Proceedings of the 21st International Conference on Autonomous Agents and Multiagent Systems, pp. 525\u2013533 (2022)"},{"key":"1_CR20","unstructured":"Heidari, H., Ferrari, C., Gummadi, K., Krause, A.: Fairness behind a veil of ignorance: a welfare analysis for automated decision making. In: Advances in Neural Information Processing Systems, vol. 31 (2018)"},{"key":"1_CR21","unstructured":"Jabbari, S., Joseph, M., Kearns, M., Morgenstern, J., Roth, A.: Fairness in reinforcement learning. In: International Conference on Machine Learning, pp. 1617\u20131626. PMLR (2017)"},{"key":"1_CR22","unstructured":"Jiang, J., Lu, Z.: Learning fairness in multi-agent systems. In: Advances in Neural Information Processing Systems, vol. 32 (2019)"},{"key":"1_CR23","unstructured":"Konidaris, G., Kuindersma, S., Barto, A., Grupen, R.: Constructing skill trees for reinforcement learning agents from demonstration trajectories. In: NIPS (2010)"},{"key":"1_CR24","unstructured":"Liu, Y., Koenig, S.: Risk-sensitive planning with one-switch utility functions: Value iteration. In: AAAI, pp. 993\u2013999. AAAI (2005)"},{"key":"1_CR25","doi-asserted-by":"publisher","unstructured":"Lov\u00e1sz, L.: Submodular functions and convexity. In: Bachem, A., Korte, B., Gr\u00f6tschel, M. (eds.) Mathematical Programming the State of the Art, pp. 235\u2013257. Springer, Berlin (1983). https:\/\/doi.org\/10.1007\/978-3-642-68874-4_10","DOI":"10.1007\/978-3-642-68874-4_10"},{"key":"1_CR26","unstructured":"Mandal, D., Gan, J.: Socially fair reinforcement learning. arXiv preprint arXiv:2208.12584 (2022)"},{"key":"1_CR27","unstructured":"Mnih, V., et al.: Asynchronous methods for deep reinforcement learning. In: ICML (2016)"},{"key":"1_CR28","doi-asserted-by":"publisher","first-page":"529","DOI":"10.1038\/nature14236","volume":"518","author":"V Mnih","year":"2015","unstructured":"Mnih, V., et al.: Human-level control through deep reinforcement learning. Nature 518, 529\u2013533 (2015)","journal-title":"Nature"},{"key":"1_CR29","doi-asserted-by":"crossref","unstructured":"Moulin, H.: Fair Division and Collective Welfare. MIT Press, Cambridge (2004)","DOI":"10.7551\/mitpress\/2954.001.0001"},{"key":"1_CR30","unstructured":"Nabi, R., Malinsky, D., Shpitser, I.: Learning optimal fair policies. In: ICML (2019)"},{"key":"1_CR31","doi-asserted-by":"crossref","unstructured":"Nardi, L., Stachniss, C.: Uncertainty-aware path planning for navigation on road networks using augmented MDPs. In: ICRA (2019)","DOI":"10.1109\/ICRA.2019.8794121"},{"key":"1_CR32","doi-asserted-by":"crossref","unstructured":"Nath, S., Baranwal, M., Khadilkar, H.: Revisiting state augmentation methods for reinforcement learning with stochastic delays. In: CIKM (2021)","DOI":"10.1145\/3459637.3482386"},{"key":"1_CR33","doi-asserted-by":"crossref","unstructured":"Neidhardt, A., Luss, H., Krishnan, K.R.: Data fusion and optimal placement of fixed and mobile sensors. In: 2008 IEEE Sensors Applications Symposium, February 2008","DOI":"10.1109\/SAS13374.2008.4472957"},{"key":"1_CR34","doi-asserted-by":"crossref","unstructured":"Nguyen, V.H., Weng, P.: An efficient primal-dual algorithm for fair combinatorial optimization problems. In: COCOA (2017)","DOI":"10.1007\/978-3-319-71150-8_28"},{"key":"1_CR35","doi-asserted-by":"crossref","unstructured":"Ogryczak, W., Luss, H., Pi\u00f3ro, M., Nace, D., Tomaszewski, A.: Fair optimization and networks: a survey. J. Appl. Math. 2014 (2014)","DOI":"10.1155\/2014\/612018"},{"issue":"05","key":"1_CR36","doi-asserted-by":"publisher","first-page":"1021","DOI":"10.1142\/S0219622013400075","volume":"12","author":"W Ogryczak","year":"2013","unstructured":"Ogryczak, W., Perny, P., Weng, P.: A compromise programming approach to multiobjective markov decision processes. Int. J. Inf. Technol. Decis. Making 12(05), 1021\u20131053 (2013)","journal-title":"Int. J. Inf. Technol. Decis. Making"},{"key":"1_CR37","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"804","DOI":"10.1007\/978-3-540-74472-6_66","volume-title":"Computational Science and Its Applications \u2013 ICCSA 2007","author":"W Ogryczak","year":"2007","unstructured":"Ogryczak, W., \u015aliwi\u0144ski, T.: On optimization of the importance weighted OWA aggregation of multiple criteria. In: Gervasi, O., Gavrilova, M.L. (eds.) ICCSA 2007. LNCS, vol. 4705, pp. 804\u2013817. Springer, Heidelberg (2007). https:\/\/doi.org\/10.1007\/978-3-540-74472-6_66"},{"key":"1_CR38","doi-asserted-by":"crossref","unstructured":"Ogryczak, W., \u015aliwi\u0144ski, T.: On solving optimization problems with ordered average criteria and constraints. In: Fuzzy Optimization: Recent Advances and Applications, pp. 209\u2013230 (2010)","DOI":"10.1007\/978-3-642-13935-2_10"},{"key":"1_CR39","unstructured":"Perny, P., Weng, P., Goldsmith, J., Hanna, J.: Approximation of lorenz-optimal solutions in multiobjective Markov decision processes. In: AAAI - Late Breaking Paper (2013)"},{"key":"1_CR40","doi-asserted-by":"crossref","unstructured":"Puterman, M.: Markov decision processes: discrete stochastic dynamic programming. Wiley (1994)","DOI":"10.1002\/9780470316887"},{"key":"1_CR41","doi-asserted-by":"crossref","unstructured":"Rawls, J.: The Theory of Justice. Havard University Press, Cambridge (1971)","DOI":"10.4159\/9780674042605"},{"key":"1_CR42","unstructured":"Ruffy, F., Przystupa, M., Beschastnikh, I.: Iroko: a framework to prototype reinforcement learning for data center traffic control. In: Workshop on ML for Systems at NeurIPS (2019). arxiv.org\/abs\/1812.09975"},{"key":"1_CR43","unstructured":"Schulman, J., Wolski, F., Dhariwal, P., Radford, A., Klimov, O.: Proximal policy optimization algorithms. CoRR abs\/1707.06347 (2017). arxiv.org\/abs\/1707.06347"},{"key":"1_CR44","unstructured":"Sharifi-Malvajerdi, S., Kearns, M., Roth, A.: Average individual fairness: algorithms, generalization and experiments. In: Advances in Neural Information Processing Systems (2019)"},{"issue":"1","key":"1_CR45","doi-asserted-by":"publisher","first-page":"5","DOI":"10.1109\/SURV.2013.050113.00015","volume":"16","author":"H Shi","year":"2014","unstructured":"Shi, H., Prasad, R.V., Onur, E., Niemegeers, I.G.M.M.: Fairness in wireless networks:issues, measures and challenges. IEEE Commun. Surv. Tutorials 16(1), 5\u201324 (2014)","journal-title":"IEEE Commun. Surv. Tutorials"},{"key":"1_CR46","unstructured":"Siddique, U., Weng, P., Zimmer, M.: Learning fair policies in multi-objective (deep) reinforcement learning with average and discounted rewards. In: ICML (2020)"},{"key":"1_CR47","unstructured":"Singh, A., Joachims, T.: Policy learning for fairness in ranking. In: Advances in Neural Information Processing Systems (2019)"},{"key":"1_CR48","unstructured":"Sootla, A., et al.: Saut\u00e9 rl: almost surely safe reinforcement learning using state augmentation. In: ICML (2022)"},{"key":"1_CR49","doi-asserted-by":"crossref","unstructured":"Speicher, T., et al.: A unified approach to quantifying algorithmic unfairness: measuring individual & group unfairness via inequality indices. In: Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, pp. 2239\u20132248 (2018)","DOI":"10.1145\/3219819.3220046"},{"key":"1_CR50","unstructured":"Sun, A., Chen, B., Doan, X.V.: Connections between fairness criteria and efficiency for allocating indivisible chores. arXiv preprint arXiv:2101.07435 (2021)"},{"key":"1_CR51","unstructured":"Sutton, R.S., McAllester, D., Singh, S., Mansour, Y.: Policy gradient methods for reinforcement learning with function approximation. In: NIPS (2000)"},{"issue":"1","key":"1_CR52","first-page":"3483","volume":"15","author":"K Van Moffaert","year":"2014","unstructured":"Van Moffaert, K., Now\u00e9, A.: Multi-objective reinforcement learning using sets of pareto dominating policies. J. Mach. Learn. Res. 15(1), 3483\u20133512 (2014)","journal-title":"J. Mach. Learn. Res."},{"key":"1_CR53","unstructured":"Wen, M., Bastani, O., Topcu, U.: Algorithms for fairness in sequential decision making. In: ICML (2021)"},{"key":"1_CR54","unstructured":"Weng, P.: Fairness in reinforcement learning. arXiv preprint arXiv:1907.10323 (2019)"},{"key":"1_CR55","unstructured":"Zafar, M.B., Valera, I., Rodriguez, M.G., Gummadi, K.P., Weller, A.: From Parity to Preference-based Notions of Fairness in Classification. In: Advances in Neural Information Processing Systems (2017)"},{"key":"1_CR56","series-title":"Studies in Systems, Decision and Control","doi-asserted-by":"publisher","first-page":"525","DOI":"10.1007\/978-3-030-60990-0_18","volume-title":"Handbook of Reinforcement Learning and Control","author":"X Zhang","year":"2021","unstructured":"Zhang, X., Liu, M.: Fairness in learning-based sequential decision algorithms: a survey. In: Vamvoudakis, K.G., Wan, Y., Lewis, F.L., Cansever, D. (eds.) Handbook of Reinforcement Learning and Control. SSDC, vol. 325, pp. 525\u2013555. Springer, Cham (2021). https:\/\/doi.org\/10.1007\/978-3-030-60990-0_18"},{"key":"1_CR57","unstructured":"Zimmer, M.: Apprentissage par renforcement developpemental. Ph.D. thesis, University of Lorraine, January 2018"},{"key":"1_CR58","unstructured":"Zimmer, M., Glanois, C., Siddique, U., Weng, P.: Learning fair policies in decentralized cooperative multi-agent reinforcement learning. In: International Conference on Machine Learning, pp. 12967\u201312978. PMLR (2021)"}],"container-title":["Lecture Notes in Computer Science","Autonomous Agents and Multiagent Systems. Best and Visionary Papers"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-56255-6_1","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,29]],"date-time":"2024-03-29T11:02:10Z","timestamp":1711710130000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-56255-6_1"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"ISBN":["9783031562549","9783031562556"],"references-count":58,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-56255-6_1","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2024]]},"assertion":[{"value":"30 March 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"AAMAS","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Autonomous Agents and Multiagent Systems","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"London","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"United Kingdom","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2023","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"29 May 2023","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"29 May 2023","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"atal2023","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/aamas2023.soton.ac.uk\/program\/accepted-workshops\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}