{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,10]],"date-time":"2026-04-10T16:27:42Z","timestamp":1775838462910,"version":"3.50.1"},"reference-count":186,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"4","license":[{"start":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T00:00:00Z","timestamp":1775001600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T00:00:00Z","timestamp":1775001600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T00:00:00Z","timestamp":1775001600000},"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":["IEEE Trans. Artif. Intell."],"published-print":{"date-parts":[[2026,4]]},"DOI":"10.1109\/tai.2025.3610590","type":"journal-article","created":{"date-parts":[[2025,9,18]],"date-time":"2025-09-18T17:49:09Z","timestamp":1758217749000},"page":"1819-1834","source":"Crossref","is-referenced-by-count":2,"title":["Towards Sample-Efficiency and Generalization of Transfer and Inverse Reinforcement Learning: A Comprehensive Literature Review"],"prefix":"10.1109","volume":"7","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-3979-9166","authenticated-orcid":false,"given":"Hossein","family":"Hassani","sequence":"first","affiliation":[{"name":"Department of Mechanical, Industrial, and Mechatronics Engineering, Toronto Metropolitan University, Toronto, ON, Canada"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9956-4003","authenticated-orcid":false,"given":"Ehsan","family":"Hallaji","sequence":"additional","affiliation":[{"name":"Department of Electrical and Computer Engineering, University of Windsor, Windsor, ON, Canada"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4330-3656","authenticated-orcid":false,"given":"Roozbeh","family":"Razavi-Far","sequence":"additional","affiliation":[{"name":"Faculty of Computer Science, University of New Brunswick, Fredericton, NB, Canada"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7587-4189","authenticated-orcid":false,"given":"Mehrdad","family":"Saif","sequence":"additional","affiliation":[{"name":"Department of Electrical and Computer Engineering, University of Windsor, Windsor, ON, Canada"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2248-3755","authenticated-orcid":false,"given":"Liang","family":"Lin","sequence":"additional","affiliation":[{"name":"School of Computer Science, Sun Yat-sen University, Guangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/j.compchemeng.2020.106886"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1016\/j.artint.2023.103859"},{"key":"ref3","volume-title":"Artificial Intelligence: A Modern Approach","author":"Russell","year":"2010"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1016\/j.artint.2021.103627"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2021.107787"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1016\/j.artint.2021.103477"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1016\/j.engappai.2020.104150"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2019.03.008"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2021.09.003"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2020.09.007"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1016\/j.apenergy.2022.118861"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1016\/j.artint.2023.103923"},{"key":"ref13","volume-title":"Reinforcement Learning: An Introduction.","author":"Sutton","year":"2018"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.2022.3214221"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1016\/j.artint.2023.103949"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3069728"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/s10462-020-09938-y"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3109284"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2016.2609500"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1016\/j.artint.2023.103905"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TETCI.2022.3140380"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2023.3292075"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3106635"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1016\/j.compeleceng.2021.107117"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1016\/j.artint.2021.103455"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2022.3148376"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1016\/j.artint.2021.103500"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.3389\/frobt.2021.584075"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992698"},{"key":"ref30","first-page":"1038","article-title":"Generalization in reinforcement learning: Successful examples using sparse coarse coding","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"8","author":"Sutton","year":"1995"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992696"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.1983.6313077"},{"key":"ref33","article-title":"Proximal policy optimization algorithms","author":"Schulman","year":"2017"},{"key":"ref34","first-page":"1889","article-title":"Trust region policy optimization","volume-title":"Proc. ICML","author":"Schulman","year":"2015"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1016\/j.ejor.2021.10.045"},{"key":"ref36","first-page":"278","article-title":"Policy invariance under reward transformations: Theory and application to reward shaping","volume-title":"Proc. ICML","volume":"99","author":"Ng","year":"1999"},{"key":"ref37","first-page":"792","article-title":"Principled methods for advising reinforcement learning agents","volume-title":"Proc. 20th Int. Conf. Mach. Learn.","author":"Wiewiora","year":"2003"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1145\/279943.279964"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1007\/s10462-021-10108-x"},{"key":"ref40","first-page":"2","article-title":"Algorithms for inverse reinforcement learning","volume-title":"Proc. ICML","volume":"1","author":"Ng","year":"2000"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1145\/1015330.1015430"},{"key":"ref42","first-page":"2393","article-title":"Interactive inverse reinforcement learning for cooperative games","volume-title":"Proc. ICML","author":"B\u00fcning","year":"2022"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRev.106.620"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3051012"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1214\/21-AOAS1529"},{"key":"ref46","article-title":"Human-in-the-loop methods for data-driven and reinforcement learning systems","author":"Goecks","year":"2020"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/PerComWorkshops48775.2020.9156175"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1007\/s10462-022-10246-w"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1145\/1597735.1597738"},{"key":"ref50","first-page":"4300","article-title":"Deep reinforcement learning from human preferences","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"30","author":"Christiano","year":"2017"},{"key":"ref51","article-title":"DQN-TAMER: Human\u2013in\u2013the\u2013loop reinforcement learning with intractable feedback","author":"Arakawa","year":"2018"},{"key":"ref52","article-title":"Humans are not Boltzmann distributions: Challenges and opportunities for modelling human feedback and interaction in reinforcement learning","author":"Lindner","year":"2022"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.3035728"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA46639.2022.9812442"},{"key":"ref55","article-title":"Human instruction-following with deep reinforcement learning via transfer-learning from text","author":"Hill","year":"2020"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1145\/3320435.3320471"},{"key":"ref57","article-title":"Advice conformance verification by reinforcement learning agents for human-in-the-loop","author":"Verma","year":"2022"},{"key":"ref58","first-page":"21885","article-title":"Widening the pipeline in human-guided reinforcement learning with explanation and context-aware data augmentation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Guan","year":"2021"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11757"},{"key":"ref60","article-title":"Leveraging demonstrations for deep reinforcement learning on robotics problems with sparse rewards","author":"Vecerik","year":"2017"},{"key":"ref61","article-title":"Observe and look further: Achieving consistent performance on Atari","author":"Pohlen","year":"2018"},{"key":"ref62","article-title":"Distributed prioritized experience replay","author":"Horgan","year":"2018"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/SSCI47803.2020.9308468"},{"key":"ref64","first-page":"734","article-title":"Sim-to-real reinforcement learning for deformable object manipulation","volume-title":"Proc. Conf. Robot Learn.","author":"Matas","year":"2018"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1017\/s0263574722001230"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2021.3084880"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2019.2894216"},{"key":"ref68","volume-title":"Real-World Robotic Perception and Control Using Synthetic Data","author":"Tobin","year":"2019"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.5220\/0009821603140323"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/IROS47612.2022.9981319"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2021.3052391"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/IROS45743.2020.9341771"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1016\/j.robot.2023.104425"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA40945.2020.9196540"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/iros55552.2023.10341769"},{"key":"ref76","article-title":"Learning to adapt in dynamic, real-world environments through meta-reinforcement learning","author":"Nagabandi","year":"2018"},{"key":"ref77","article-title":"RL2: Fast reinforcement learning via slow reinforcement learning","author":"Duan","year":"2016"},{"key":"ref78","first-page":"1126","article-title":"Model-agnostic meta-learning for fast adaptation of deep networks","volume-title":"Proc. ICML","author":"Finn","year":"2017"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA40945.2020.9197326"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1109\/ICAR53236.2021.9659351"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9561731"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9561982"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9561302"},{"key":"ref84","article-title":"Adaptive policy transfer in reinforcement learning","author":"Joshi","year":"2021"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1109\/ICMLA52953.2021.00079"},{"key":"ref86","article-title":"Multipolar: Multi-source policy aggregation for transfer reinforcement learning between diverse environmental dynamics","author":"Barekatain","year":"2019"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2020\/428"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.3390\/e24040470"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2021.3108237"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2022.3167029"},{"key":"ref91","first-page":"10141","article-title":"Repaint: Knowledge transfer in deep reinforcement learning","volume-title":"Proc. ICML","author":"Tao","year":"2021"},{"key":"ref92","first-page":"1787","article-title":"Contextual policy transfer in reinforcement learning domains via deep mixtures\u2013of\u2013experts","volume-title":"Proc. Uncertainty Artif. Intell.","author":"Gimelfarb","year":"2021"},{"key":"ref93","article-title":"Jointly pre-training with supervised, autoencoder, and value losses for deep reinforcement learning","author":"Cruz","year":"2019"},{"key":"ref94","article-title":"Agent-agnostic human-in-the-loop reinforcement learning","author":"Abel","year":"2017"},{"key":"ref95","article-title":"interactive reinforcement learning with dynamic reuse of prior knowledge from human\/agent\u2019s demonstration","author":"Wang","year":"2018"},{"key":"ref96","article-title":"Single episode policy transfer in reinforcement learning","author":"Yang","year":"2019"},{"key":"ref97","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-29946-9_27"},{"key":"ref98","first-page":"2586","article-title":"Bayesian inverse reinforcement learning","volume-title":"Proc. IJCAI","volume":"7","author":"Ramachandran","year":"2007"},{"key":"ref99","first-page":"897","article-title":"Apprenticeship learning about multiple intentions","volume-title":"Proc. 28th Int. Conf. Mach. Learn.","author":"Babes","year":"2011"},{"key":"ref100","first-page":"668","article-title":"Nonparametric Bayesian inverse reinforcement learning for multiple reward functions","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"25","author":"Choi","year":"2012"},{"key":"ref101","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-86486-6_13"},{"key":"ref102","doi-asserted-by":"publisher","DOI":"10.1214\/16-AOS1435"},{"key":"ref103","article-title":"LiMIIRL: Lightweight multiple-intent inverse reinforcement learning","author":"Snoswell","year":"2021"},{"key":"ref104","first-page":"2359","article-title":"Truly batch model-free inverse reinforcement learning about multiple intentions","volume-title":"Proc. Int. Conf. Artif. Intell. Statist.","author":"Ramponi","year":"2020"},{"key":"ref105","article-title":"Multi-agent inverse reinforcement learning: Suboptimal demonstrations and alternative solution concepts","author":"Bergerson","year":"2021"},{"key":"ref106","article-title":"Agent-level maximum entropy inverse reinforcement learning for mean field games","author":"Chen","year":"2021"},{"key":"ref107","first-page":"3305","article-title":"PsiPhi-Learning: Reinforcement learning with demonstrations using successor features and inverse temporal difference learning","volume-title":"Proc. ICML","author":"Filos","year":"2021"},{"key":"ref108","doi-asserted-by":"publisher","DOI":"10.1007\/s10994-020-05939-8"},{"key":"ref109","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2021.3060411"},{"key":"ref110","first-page":"7194","article-title":"Multi-agent adversarial inverse reinforcement learning","volume-title":"Proc. ICML","author":"Yu","year":"2019"},{"key":"ref111","article-title":"Scalable multi-agent inverse reinforcement learning via actor-attention-critic","author":"Jeon","year":"2020"},{"key":"ref112","doi-asserted-by":"publisher","DOI":"10.3389\/frai.2021.625183"},{"key":"ref113","doi-asserted-by":"publisher","DOI":"10.1109\/SSCI47803.2020.9308491"},{"key":"ref114","doi-asserted-by":"publisher","DOI":"10.1007\/s10458-020-09485-4"},{"key":"ref115","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA40945.2020.9197126"},{"key":"ref116","doi-asserted-by":"publisher","DOI":"10.1145\/3422622"},{"key":"ref117","article-title":"Generative adversarial imitation learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"29","author":"Ho","year":"2016"},{"key":"ref118","doi-asserted-by":"publisher","DOI":"10.1109\/CDC.2014.7040156"},{"key":"ref119","article-title":"A connection between generative adversarial networks, inverse reinforcement learning, and energy-based models","author":"Finn","year":"2016"},{"key":"ref120","article-title":"Learning robust rewards with adversarial inverse reinforcement learning","author":"Fu","year":"2017"},{"key":"ref121","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11775"},{"key":"ref122","article-title":"Situated GAIL: Multitask imitation using task-conditioned adversarial inverse reinforcement learning","author":"Kobayashi","year":"2019"},{"key":"ref123","volume-title":"Robust Adversarial Inverse Reinforcement Learning with Temporally Extended Actions","author":"Venuto","year":"2020"},{"key":"ref124","article-title":"Off-policy adversarial inverse reinforcement learning","author":"Arnob","year":"2020"},{"key":"ref125","first-page":"1259","article-title":"A divergence minimization perspective on imitation learning methods","volume-title":"Proc. Conf. Robot Learn.","author":"Ghasemipour","year":"2020"},{"key":"ref126","article-title":"f-IRL: Inverse reinforcement learning via state marginal matching","author":"Ni","year":"2020"},{"key":"ref127","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9561330"},{"key":"ref128","first-page":"3138","article-title":"Sample-efficient imitation learning via generative adversarial nets","volume-title":"Proc. 22nd Int. Conf. Artif. Intell. Statist.","author":"Blond\u00e9","year":"2019"},{"key":"ref129","article-title":"Sample efficient actor-critic with experience replay","author":"Wang","year":"2016"},{"key":"ref130","doi-asserted-by":"publisher","DOI":"10.32657\/10356\/90191"},{"key":"ref131","article-title":"Sample efficient imitation learning for continuous control","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Sasaki","year":"2018"},{"key":"ref132","article-title":"Off-policy actor-critic","author":"Degris","year":"2012"},{"key":"ref133","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA46639.2022.9811660"},{"key":"ref134","doi-asserted-by":"publisher","DOI":"10.1109\/IROS45743.2020.9340915"},{"key":"ref135","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2020.3005126"},{"key":"ref136","first-page":"1861","article-title":"Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor","volume-title":"Proc. ICML","author":"Haarnoja","year":"2018"},{"key":"ref137","article-title":"Discriminator-actor-critic: Addressing sample inefficiency and reward bias in adversarial imitation learning","author":"Kostrikov","year":"2018"},{"key":"ref138","article-title":"Sample efficient social navigation using inverse reinforcement learning","author":"Baghi","year":"2021"},{"key":"ref139","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-97304-3_25"},{"key":"ref140","doi-asserted-by":"publisher","DOI":"10.1109\/tnnls.2023.3305983"},{"key":"ref141","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2923993"},{"key":"ref142","doi-asserted-by":"publisher","DOI":"10.1109\/TIFS.2022.3149396"},{"key":"ref143","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2021.106967"},{"key":"ref144","doi-asserted-by":"publisher","DOI":"10.1109\/MWC.001.1900207"},{"key":"ref145","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2022.3194694"},{"key":"ref146","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3114612"},{"key":"ref147","doi-asserted-by":"publisher","DOI":"10.23919\/ACC.2018.8430922"},{"key":"ref148","doi-asserted-by":"publisher","DOI":"10.1109\/SRDS53918.2021.00037"},{"key":"ref149","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2024.128836"},{"key":"ref150","doi-asserted-by":"publisher","DOI":"10.1016\/j.engappai.2024.109147"},{"key":"ref151","doi-asserted-by":"publisher","DOI":"10.1049\/itr2.12172"},{"key":"ref152","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2019.06.067"},{"key":"ref153","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2022.3202185"},{"key":"ref154","doi-asserted-by":"publisher","DOI":"10.1016\/j.robot.2019.01.003"},{"key":"ref155","doi-asserted-by":"publisher","DOI":"10.1177\/1729881418817162"},{"key":"ref156","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2021.3121985"},{"key":"ref157","doi-asserted-by":"publisher","DOI":"10.52202\/068431-2011"},{"key":"ref158","first-page":"1877","article-title":"Language models are few-shot learners","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Brown","year":"2020"},{"key":"ref159","doi-asserted-by":"publisher","DOI":"10.1016\/j.cie.2024.110855"},{"key":"ref160","doi-asserted-by":"publisher","DOI":"10.1016\/j.asoc.2024.112689"},{"key":"ref161","doi-asserted-by":"publisher","DOI":"10.1016\/j.cor.2024.106919"},{"key":"ref162","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.2024.3449413"},{"key":"ref163","first-page":"1273","article-title":"Communication-efficient learning of deep networks from decentralized data","volume-title":"Proc. Artif. Intell. Statist.","author":"McMahan","year":"2017"},{"key":"ref164","article-title":"Federated learning: Strategies for improving communication efficiency","author":"Kone\u010dn\u1ef3","year":"2016"},{"key":"ref165","doi-asserted-by":"publisher","DOI":"10.20517\/ir.2021.02"},{"key":"ref166","first-page":"10997","article-title":"Federated reinforcement learning: Linear speedup under Markovian sampling","volume-title":"Proc. ICML","author":"Khodadadian","year":"2022"},{"key":"ref167","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2022.3190557"},{"key":"ref168","doi-asserted-by":"publisher","DOI":"10.1109\/CAMAD55695.2022.9966919"},{"key":"ref169","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-11748-0_15"},{"key":"ref170","doi-asserted-by":"publisher","DOI":"10.1109\/HPSR52026.2021.9481851"},{"key":"ref171","article-title":"Self-paced multi-agent reinforcement learning","author":"Zhao","year":"2022"},{"key":"ref172","article-title":"Teacher-student curriculum learning for reinforcement learning","author":"Schraner","year":"2022"},{"key":"ref173","doi-asserted-by":"publisher","DOI":"10.52202\/068431-0774"},{"key":"ref174","article-title":"Human decision makings on curriculum reinforcement learning with difficulty adjustment","author":"Zeng","year":"2022"},{"key":"ref175","doi-asserted-by":"publisher","DOI":"10.1109\/IROS47612.2022.9981109"},{"key":"ref176","article-title":"Effects of reward shaping on curriculum learning in goal conditioned tasks","author":"Anca","year":"2022"},{"key":"ref177","doi-asserted-by":"publisher","DOI":"10.1109\/ALLERTON.2018.8636075"},{"key":"ref178","doi-asserted-by":"publisher","DOI":"10.5220\/0006671802430249"},{"key":"ref179","doi-asserted-by":"publisher","DOI":"10.1109\/ICCE-Asia49877.2020.9276975"},{"key":"ref180","article-title":"Prioritized experience replay","author":"Schaul","year":"2015"},{"key":"ref181","doi-asserted-by":"publisher","DOI":"10.1109\/ICIVC.2017.7984718"},{"key":"ref182","doi-asserted-by":"publisher","DOI":"10.1109\/DEVLRN.2019.8850705"},{"key":"ref183","article-title":"Curiosity-driven experience prioritization via density estimation","author":"Zhao","year":"2019"},{"key":"ref184","first-page":"110","article-title":"Experience replay with likelihood-free importance weights","volume-title":"Proc. Learn. Dyn. Control Conf.","author":"Sinha","year":"2022"},{"key":"ref185","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2021.116023"},{"key":"ref186","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3223407"}],"container-title":["IEEE Transactions on Artificial Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/9078688\/11458162\/11170411.pdf?arnumber=11170411","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T06:17:01Z","timestamp":1775024221000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11170411\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4]]},"references-count":186,"journal-issue":{"issue":"4"},"URL":"https:\/\/doi.org\/10.1109\/tai.2025.3610590","relation":{},"ISSN":["2691-4581"],"issn-type":[{"value":"2691-4581","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,4]]}}}