{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T17:24:45Z","timestamp":1777656285345,"version":"3.51.4"},"reference-count":43,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"9","license":[{"start":{"date-parts":[[2025,9,1]],"date-time":"2025-09-01T00:00:00Z","timestamp":1756684800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,9,1]],"date-time":"2025-09-01T00:00:00Z","timestamp":1756684800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,9,1]],"date-time":"2025-09-01T00:00:00Z","timestamp":1756684800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["CCF-2438429"],"award-info":[{"award-number":["CCF-2438429"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["ECCS-2438392"],"award-info":[{"award-number":["ECCS-2438392"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"name":"NSF","award":["CCF-2311274"],"award-info":[{"award-number":["CCF-2311274"]}]},{"name":"NSF","award":["ECCS-2326592"],"award-info":[{"award-number":["ECCS-2326592"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Inform. Theory"],"published-print":{"date-parts":[[2025,9]]},"DOI":"10.1109\/tit.2025.3581454","type":"journal-article","created":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T13:37:42Z","timestamp":1750340262000},"page":"7254-7269","source":"Crossref","is-referenced-by-count":1,"title":["Theoretical Study of Conflict-Avoidant Multi-Objective Reinforcement Learning"],"prefix":"10.1109","volume":"71","author":[{"given":"Yudan","family":"Wang","sequence":"first","affiliation":[{"name":"School of Electrical, Computer and Energy Engineering, Arizona State University, Tempe, AZ, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Peiyao","family":"Xiao","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Engineering, University at Buffalo, Buffalo, NY, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-4680-2233","authenticated-orcid":false,"given":"Hao","family":"Ban","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Engineering, University at Buffalo, Buffalo, NY, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9533-0058","authenticated-orcid":false,"given":"Kaiyi","family":"Ji","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Engineering, University at Buffalo, Buffalo, NY, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2821-6941","authenticated-orcid":false,"given":"Shaofeng","family":"Zou","sequence":"additional","affiliation":[{"name":"School of Electrical, Computer and Energy Engineering, Arizona State University, Tempe, AZ, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2016.2522401"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.2352\/ISSN.2470-1173.2017.19.AVM-023"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2017.7989385"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1177\/0278364912472380"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1177\/0278364919887447"},{"key":"ref6","first-page":"1","article-title":"Provable multi-objective reinforcement learning with generative models","volume-title":"Proc. Workshop Real-World Reinforcement Learn. 34th Conf. Neural Inf. Process. Syst. (NeurIPS)","author":"Zhou"},{"key":"ref7","first-page":"1046","article-title":"Finite-time complexity of incremental policy gradient methods for solving multi-task reinforcement learning","volume-title":"Proc. 6th Annu. Learn. Dyn. Control Conf.","author":"Bai"},{"key":"ref8","first-page":"1563","article-title":"The steering approach for multi-criteria reinforcement learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NIPS)","volume":"14","author":"Mannor"},{"key":"ref9","first-page":"14636","article-title":"A generalized algorithm for multi-objective reinforcement learning and policy adaptation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Yang"},{"key":"ref10","first-page":"1","article-title":"Three-way trade-off in multi-objective learning: Optimization, generalization and conflict-avoidance","volume-title":"Proc. NeurIPS","author":"Chen"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2023.3271445"},{"key":"ref12","first-page":"5824","article-title":"Gradient surgery for multi-task learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NeurIPS)","volume":"33","author":"Yu"},{"key":"ref13","first-page":"18878","article-title":"Conflict-averse gradient descent for multi-task learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NeurIPS)","author":"Liu"},{"key":"ref14","first-page":"16428","article-title":"Multi-task learning as a bargaining game","volume-title":"Proc. Int. Conf. Mach. Learn. (ICML)","author":"Navon"},{"key":"ref15","first-page":"4509","article-title":"Direction-oriented multi-objective learning: Simple and provable stochastic algorithms","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NeurIPS)","author":"Xiao"},{"key":"ref16","first-page":"1","article-title":"Mitigating gradient bias in multi-objective learning: A provably convergent approach","volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","author":"Fernando"},{"key":"ref17","first-page":"1094","article-title":"Meta-world: A benchmark and evaluation for multi-task and meta reinforcement learning","volume-title":"Proc. Conf. Robot. Learn. (CoRL)","author":"Yu"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/s10994-010-5232-5"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.2014.2358639"},{"key":"ref20","first-page":"2961","article-title":"Actor-attention-critic for multi-agent reinforcement learning","volume-title":"Proc. 36th Int. Conf. Mach. Learn.","volume":"97","author":"Iqbal"},{"key":"ref21","first-page":"580","article-title":"Multi-task actor-critic with knowledge transfer via a shared critic","volume-title":"Proc. Asian Conf. Mach. Learn.","author":"Zhang"},{"key":"ref22","article-title":"Pareto actor-critic for equilibrium selection in multi-agent reinforcement learning","author":"Christianos","year":"2023","journal-title":"Trans. Mach. Learn. Res."},{"key":"ref23","article-title":"Accelerating multi-task temporal difference learning under low-rank representation","author":"Bai","year":"2025","journal-title":"arXiv:2503.02030"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/JSAIT.2021.3078754"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/s10994-023-06303-2"},{"key":"ref26","first-page":"1","article-title":"Improving sample complexity bounds for (Natural) actor-critic algorithms","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NeurIPS)","author":"Xu"},{"key":"ref27","first-page":"991","article-title":"Analysis of a target-based actor-critic algorithm with linear function approximation","volume-title":"Proc. 25th Int. Conf. Artif. Intell. Statist.","volume":"151","author":"Barakat"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1137\/22M1483335"},{"key":"ref29","first-page":"51771","article-title":"Non-asymptotic analysis for single-loop (Natural) actor-critic with compatible function approximation","volume-title":"Proc. 41st Int. Conf. Mach. Learn.","volume":"235","author":"Wang"},{"key":"ref30","first-page":"931","article-title":"Dcrac: Deep conditioned recurrent actor-critic for multi-objective partially observable environments","volume-title":"Proc. Int. Conf. Auto. Agents Multiagent Syst.","author":"Nian"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/s10458-023-09604-x"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1016\/j.enconman.2021.114381"},{"key":"ref33","first-page":"2039","article-title":"Just Pick a sign: Optimizing deep multitask models with gradient sign dropout","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NeurIPS)","author":"Zhao"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1137\/s0363012901385691"},{"key":"ref35","first-page":"1057","article-title":"Policy gradient methods for reinforcement learning with function approximation","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NIPS)","volume":"12","author":"Sutton"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1016\/j.crma.2012.03.014"},{"key":"ref37","first-page":"8665","article-title":"Finite-sample analysis for SARSA with linear function approximation","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NeurIPS)","volume":"32","author":"Zou"},{"key":"ref38","first-page":"17617","article-title":"A finite-time analysis of two time-scale actor-critic methods","volume-title":"Proc. NIPS","author":"Wu"},{"key":"ref39","first-page":"1861","article-title":"Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Haarnoja"},{"key":"ref40","first-page":"4767","article-title":"Multi-task reinforcement learning with soft modularization","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NeurIPS)","author":"Yang"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1287\/opre.2020.2024"},{"key":"ref42","first-page":"71","article-title":"Stochastic gradient descent for non-smooth optimization: Convergence results and optimal averaging schemes","volume-title":"Proc. 30th Int. Conf. Mach. Learn.","author":"Shamir"},{"key":"ref43","first-page":"10555","article-title":"A finite-time analysis of Q-Learning with neural network function approximation","volume-title":"Proc. Int. Conf. Mach. Learn. (ICML)","author":"Xu"}],"container-title":["IEEE Transactions on Information Theory"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/18\/11134633\/11044347.pdf?arnumber=11044347","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,25]],"date-time":"2025-08-25T20:44:37Z","timestamp":1756154677000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11044347\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,9]]},"references-count":43,"journal-issue":{"issue":"9"},"URL":"https:\/\/doi.org\/10.1109\/tit.2025.3581454","relation":{},"ISSN":["0018-9448","1557-9654"],"issn-type":[{"value":"0018-9448","type":"print"},{"value":"1557-9654","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,9]]}}}